Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs). After such a disruptive change to our understanding of the field, what is left to do? Taking a historical lens, we look for guidance from the first era of LLMs, which began in 2005 with large n-gram models for machine translation (MT). We identify durable lessons from the first era, and more importantly, we identify evergreen problems where NLP researchers can continue to make meaningful contributions in areas where LLMs are ascendant. We argue that disparities in scale are transient and researchers can work to reduce them; that data, rather than hardware, is still a bottleneck for many applications; that meaningful realistic evaluation is still an open problem; and that there is still room for speculative approaches.

The choice of hyperparameters greatly impacts performance in natural language processing. Often, it is hard to tell if a method is better than another or just better tuned. *Tuning curves* fix this ambiguity by accounting for tuning effort. Specifically, they plot validation performance as a function of the number of hyperparameter choices tried so far. While several estimators exist for these curves, it is common to use point estimates, which we show fail silently and give contradictory results when given too little data.Beyond point estimates, *confidence bands* are necessary to rigorously establish the relationship between different approaches. We present the first method to construct valid confidence bands for tuning curves. The bands are exact, simultaneous, and distribution-free, thus they provide a robust basis for comparing methods.Empirical analysis shows that while bootstrap confidence bands, which serve as a baseline, fail to approximate their target confidence, ours achieve it exactly. We validate our design with ablations, analyze the effect of sample size, and provide guidance on comparing models with our method. To promote confident comparisons in future work, we release opda: an easy-to-use library that you can install with pip. https://github.com/nicholaslourie/opda

Natural language (NL) feedback offers rich insights into user experience. While existing studies focus on an instance-level approach, where feedback is used to refine specific examples, we introduce a framework for system-level use of NL feedback. We show how to use feedback to formalize system-level design decisions in a human-in-the-loop-process – in order to produce better models. In particular this is done through: (i) metric design for tasks; and (ii) language model prompt design for refining model responses. We conduct two case studies of this approach for improving search query and dialog response generation, demonstrating the effectiveness of system-level feedback. We show the combination of system-level and instance-level feedback brings further gains, and that human written instance-level feedback results in more grounded refinements than GPT-3.5 written ones, underlying the importance of human feedback for building systems.

We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes. Our experiments use the publicly released deployment data from BlenderBot (Xu et al., 2023). Human evaluation indicates improvements in our new models over baseline responses; however, we find that some proxy signals can lead to more generations with undesirable properties as well. For example, optimizing for conversation length can lead to more controversial or unfriendly generations compared to the baseline, whereas optimizing for positive sentiment or reaction can decrease these behaviors.

Building robust and reliable machine learning systems requires models with the capacity to generalize their knowledge to interpret unseen inputs with different characteristics. Traditional language model evaluation tasks lack informative metrics about model generalization, and their applicability in new settings is often measured using task and language-specific downstream performance, which is lacking in many languages and tasks. To address this gap, we explore a set of efficient and reliable measures that could aid in computing more information related to the generalization capability of language models, particularly in cross-lingual zero-shot settings. Our central hypothesis is that the sharpness of a model’s loss landscape, i.e., the representation of loss values over its weight space, can indicate its generalization potential, with a flatter landscape suggesting better generalization. We propose a novel and stable algorithm to reliably compute the sharpness of a model optimum, and demonstrate its correlation with successful cross-lingual transfer.

In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we design and synthesize a wide range of potential errors and check whether they result in a commensurate drop in the metric scores. We examine a range of recently proposed evaluation metrics based on pretrained language models, for the tasks of open-ended generation, translation, and summarization. Our experiments reveal interesting insensitivities, biases, or even loopholes in existing metrics. For example, we find that BERTScore is confused by truncation errors in summarization, and MAUVE (built on top of GPT-2) is insensitive to errors at the beginning or middle of generations. Further, we investigate the reasons behind these blind spots and suggest practical workarounds for a more reliable evaluation of text generation. We have released our code and data at https://github.com/cloudygoose/blindspot_nlg.

Recent advances in large language models have led to renewed interest in natural language processing in healthcare using the free text of clinical notes. One distinguishing characteristic of clinical notes is their long time span over multiple long documents. The unique structure of clinical notes creates a new design choice: when the context length for a language model predictor is limited, which part of clinical notes should we choose as the input? Existing studies either choose the inputs with domain knowledge or simply truncate them. We propose a framework to analyze the sections with high predictive power. Using MIMIC-III, we show that: 1) predictive power distribution is different between nursing notes and discharge notes and 2) combining different types of notes could improve performance when the context length is large. Our findings suggest that a carefully selected sampling function could enable more efficient information extraction from clinical notes.

The Ninth Revision of the International Classification of Diseases (ICD-9) is a standardized coding system used to classify health conditions. It is used for billing, tracking individual patient conditions, and for epidemiology. The highly detailed and technical nature of the codes and their associated medical conditions make it difficult for humans to accurately record them. Researchers have explored the use of neural networks, particularly language models, for automated ICD-9 code assignment. However, the imbalanced distribution of ICD-9 codes leads to poor performance. One solution is to use domain knowledge to incorporate a useful prior. This paper evaluates the usefulness of the correlation bias: we hypothesize that correlations between ICD-9 codes and other medical codes could help improve language models’ performance. We showed that while the correlation bias worsens the overall performance, the effect on individual class can be negative or positive. Performance on classes that are more imbalanced and less correlated with other codes is more sensitive to incorporating the correlation bias. This suggests that while the correlation bias has potential to improve ICD-9 code assignment in certain cases, the applicability criteria need to be more carefully studied.

Many recent studies on large-scale language models have reported successful in-context zero- and few-shot learning ability. However, the in-depth analysis of when in-context learning occurs is still lacking. For example, it is unknown how in-context learning performance changes as the training corpus varies. Here, we investigate the effects of the source and size of the pretraining corpus on in-context learning in HyperCLOVA, a Korean-centric GPT-3 model. From our in-depth investigation, we introduce the following observations: (1) in-context learning performance heavily depends on the corpus domain source, and the size of the pretraining corpus does not necessarily determine the emergence of in-context learning, (2) in-context learning ability can emerge when a language model is trained on a combination of multiple corpora, even when each corpus does not result in in-context learning on its own, (3) pretraining with a corpus related to a downstream task does not always guarantee the competitive in-context learning performance of the downstream task, especially in the few-shot setting, and (4) the relationship between language modeling (measured in perplexity) and in-context learning does not always correlate: e.g., low perplexity does not always imply high in-context few-shot learning performance.

It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, we propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences. Besides, we investigate a multi-task learning strategy that finetunes a pre-trained neural machine translation model on both entity-augmented monolingual data and parallel data to further improve entity translation. Experimental results on three language pairs demonstrate that DEEP results in significant improvements over strong denoising auto-encoding baselines, with a gain of up to 1.3 BLEU and up to 9.2 entity accuracy points for English-Russian translation.

We present MolT5 - a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. MolT5 allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since MolT5 pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that MolT5-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.

Historical records in Korea before the 20th century were primarily written in Hanja, an extinct language based on Chinese characters and not understood by modern Korean or Chinese speakers. Historians with expertise in this time period have been analyzing the documents, but that process is very difficult and time-consuming, and language models would significantly speed up the process. Toward building and evaluating language models for Hanja, we release the Hanja Understanding Evaluation dataset consisting of chronological attribution, topic classification, named entity recognition, and summary retrieval tasks. We also present BERT-based models continued training on the two major corpora from the 14th to the 19th centuries: the Annals of the Joseon Dynasty and Diaries of the Royal Secretariats. We compare the models with several baselines on all tasks and show there are significant improvements gained by training on the two corpora. Additionally, we run zero-shot experiments on the Daily Records of the Royal Court and Important Officials (DRRI). The DRRI dataset has not been studied much by the historians, and not at all by the NLP community.

The Annals of Joseon Dynasty (AJD) contain the daily records of the Kings of Joseon, the 500-year kingdom preceding the modern nation of Korea.The Annals were originally written in an archaic Korean writing system, ‘Hanja’, and were translated into Korean from 1968 to 1993.The resulting translation was however too literal and contained many archaic Korean words; thus, a new expert translation effort began in 2012. Since then, the records of only one king have been completed in a decade.In parallel, expert translators are working on English translation, also at a slow pace and produced only one king’s records in English so far.Thus, we propose H2KE, a neural machine translation model, that translates historical documents in Hanja to more easily understandable Korean and to English.Built on top of multilingual neural machine translation, H2KE learns to translate a historical document written in Hanja, from both a full dataset of outdated Korean translation and a small dataset of more recently translated contemporary Korean and English.We compare our method against two baselines:a recent model that simultaneously learns to restore and translate Hanja historical documentand a Transformer based model trained only on newly translated corpora.The experiments reveal that our method significantly outperforms the baselines in terms of BLEU scores for both contemporary Korean and English translations.We further conduct extensive human evaluation which shows that our translation is preferred over the original expert translations by both experts and non-expert Korean speakers.

Neural autoregressive sequence models smear the probability among many possible sequences including degenerate ones, such as empty or repetitive sequences. In this work, we tackle one specific case where the model assigns a high probability to unreasonably short sequences. We define the oversmoothing rate to quantify this issue. After confirming the high degree of oversmoothing in neural machine translation, we propose to explicitly minimize the oversmoothing rate during training. We conduct a set of experiments to study the effect of the proposed regularization on both model distribution and decoding performance. We use a neural machine translation task as the testbed and consider three different datasets of varying size. Our experiments reveal three major findings. First, we can control the oversmoothing rate of the model by tuning the strength of the regularization. Second, by enhancing the oversmoothing loss contribution, the probability and the rank of eos token decrease heavily at positions where it is not supposed to be. Third, the proposed regularization impacts the outcome of beam search especially when a large beam is used. The degradation of translation quality (measured in BLEU) with a large beam significantly lessens with lower oversmoothing rate, but the degradation compared to smaller beam sizes remains to exist. From these observations, we conclude that the high degree of oversmoothing is the main reason behind the degenerate case of overly probable short sequences in a neural autoregressive model.

An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only cover limited domains, or suffer from noisy data, and most of all are typically hard to integrate into neural language pipelines. To fill this gap, we release VisualSem: a high-quality knowledge graph (KG) which includes nodes with multilingual glosses, multiple illustrative images, and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline. We encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval models are publicly available and can be downloaded in this URL: https://github.com/iacercalixto/visualsem.

Recent years have seen numerous NLP datasets introduced to evaluate the performance of fine-tuned models on natural language understanding tasks. Recent results from large pretrained models, though, show that many of these datasets are largely saturated and unlikely to be able to detect further progress. What kind of datasets are still effective at discriminating among strong models, and what kind of datasets should we expect to be able to detect future improvements? To measure this uniformly across datasets, we draw on Item Response Theory and evaluate 29 datasets using predictions from 18 pretrained Transformer models on individual test examples. We find that Quoref, HellaSwag, and MC-TACO are best suited for distinguishing among state-of-the-art models, while SNLI, MNLI, and CommitmentBank seem to be saturated for current strong models. We also observe span selection task format, which is used for QA datasets like QAMR or SQuAD2.0, is effective in differentiating between strong and weak models.

Despite transformers’ impressive accuracy, their computational cost is often prohibitive to use with limited computational resources. Most previous approaches to improve inference efficiency require a separate model for each possible computational budget. In this paper, we extend PoWER-BERT (Goyal et al., 2020) and propose Length-Adaptive Transformer that can be used for various inference scenarios after one-shot training. We train a transformer with LengthDrop, a structural variant of dropout, which stochastically determines a sequence length at each layer. We then conduct a multi-objective evolutionary search to find a length configuration that maximizes the accuracy and minimizes the efficiency metric under any given computational budget. Additionally, we significantly extend the applicability of PoWER-BERT beyond sequence-level classification into token-level classification with Drop-and-Restore process that drops word-vectors temporarily in intermediate layers and restores at the last layer if necessary. We empirically verify the utility of the proposed approach by demonstrating the superior accuracy-efficiency trade-off under various setups, including span-based question answering and text classification. Code is available at https://github.com/clovaai/lengthadaptive-transformer.

Despite its wide use, recent studies have revealed unexpected and undesirable properties of neural autoregressive sequence models trained with maximum likelihood, such as an unreasonably high affinity to short sequences after training and to infinitely long sequences at decoding time. We propose to study these phenomena by investigating how the modes, or local maxima, of a distribution are maintained throughout the full learning chain of the ground-truth, empirical, learned and decoding-induced distributions, via the newly proposed mode recovery cost. We design a tractable testbed where we build three types of ground-truth distributions: (1) an LSTM based structured distribution, (2) an unstructured distribution where probability of a sequence does not depend on its content, and (3) a product of these two which we call a semi-structured distribution. Our study reveals both expected and unexpected findings. First, starting with data collection, mode recovery cost strongly relies on the ground-truth distribution and is most costly with the semi-structured distribution. Second, after learning, mode recovery cost from the ground-truth distribution may increase or decrease compared to data collection, with the largest cost degradation occurring with the semi-structured ground-truth distribution. Finally, the ability of the decoding-induced distribution to recover modes from the learned distribution is highly impacted by the choices made earlier in the learning chain. We conclude that future research must consider the entire learning chain in order to fully understand the potentials and perils and to further improve neural autoregressive sequence models.

Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we propose AdapterFusion, a new two stage learning algorithm that leverages knowledge from multiple tasks. First, in the knowledge extraction stage we learn task specific parameters called adapters, that encapsulate the task-specific information. We then combine the adapters in a separate knowledge composition step. We show that by separating the two stages, i.e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner. We empirically evaluate AdapterFusion on 16 diverse NLU tasks, and find that it effectively combines various types of knowledge at different layers of the model. We show that our approach outperforms traditional strategies such as full fine-tuning as well as multi-task learning. Our code and adapters are available at AdapterHub.ml.

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. Our major finding is that after standard finetuning, the model forgets some of the important language generation skills acquired during large-scale pretraining. We demonstrate the forgetting phenomenon through a set of detailed behavior analysis from the perspectives of knowledge transfer, context sensitivity, and function space projection. As a preliminary attempt to alleviate the forgetting problem, we propose an intuitive finetuning strategy named “mix-review”. We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent. Finally, we discuss interesting behavior of the resulting dialogue model and its implications.

Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.

Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations by schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 17.8% on HITS@1.

We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI. Our system has been online and serving users since late March 2020. The Covidex is the user application component of our three-pronged strategy to develop technologies for helping domain experts tackle the ongoing global pandemic. In addition, we provide robust and easy-to-use keyword search infrastructure that exploits mature fusion-based methods as well as standalone neural ranking models that can be incorporated into other applications. These techniques have been evaluated in the multi-round TREC-COVID challenge: Our infrastructure and baselines have been adopted by many participants, including some of the best systems. In round 3, we submitted the highest-scoring run that took advantage of previous training data and the second-highest fully automatic run. In rounds 4 and 5, we submitted the highest-scoring fully automatic runs.

The interaction of conversational systems with users poses an exciting opportunity for improving them after deployment, but little evidence has been provided of its feasibility. In most applications, users are not able to provide the correct answer to the system, but they are able to provide binary (correct, incorrect) feedback. In this paper we propose feedback-weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback. We perform simulated experiments on document classification (for development) and Conversational Question Answering datasets like QuAC and DoQA, where binary user feedback is derived from gold annotations. The results show that our method is able to improve over the initial supervised system, getting close to a fully-supervised system that has access to the same labeled examples in in-domain experiments (QuAC), and even matching in out-of-domain experiments (DoQA). Our work opens the prospect to exploit interactions with real users and improve conversational systems after deployment.

This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling methods (top-k, nucleus and tempered sampling). We focus on the task of open-ended language generation, and first show that the existing sampling algorithms have similar performance. By carefully inspecting the transformations defined by different sampling algorithms, we identify three key properties that are shared among them: entropy reduction, order preservation, and slope preservation. To validate the importance of the identified properties, we design two sets of new sampling methods: one set in which each algorithm satisfies all three properties, and one set in which each algorithm violates at least one of the properties. We compare their performance with existing algorithms, and find that violating the identified properties could lead to drastic performance degradation, as measured by the Q-D trade-off. On the other hand, we find that the set of sampling algorithms that satisfy these properties performs on par with the existing sampling algorithms.

Recent works have discussed the extent to which emergent languages can exhibit properties of natural languages particularly learning compositionality. In this paper, we investigate the learning biases that affect the efficacy and compositionality in multi-agent communication in addition to the communicative bandwidth. Our foremost contribution is to explore how the capacity of a neural network impacts its ability to learn a compositional language. We additionally introduce a set of evaluation metrics with which we analyze the learned languages. Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization. While we empirically see evidence for the bottom of this range, we curiously do not find evidence for the top part of the range and believe that this is an open question for the community.

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within utterances, (iii) overuse frequent words, and (iv) at a deeper level, contain logical flaws. In this work we show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019) to these cases. We show that appropriate loss functions which regularize generated outputs to match human distributions are effective for the first three issues. For the last important general issue, we show applying unlikelihood to collected data of what a model should not do is effective for improving logical consistency, potentially paving the way to generative models with greater reasoning ability. We demonstrate the efficacy of our approach across several dialogue tasks.

Practical applications of abstractive summarization models are limited by frequent factual inconsistencies with respect to their input. Existing automatic evaluation metrics for summarization are largely insensitive to such errors. We propose QAGS (pronounced “kags”), an automatic evaluation protocol that is designed to identify factual inconsistencies in a generated summary. QAGS is based on the intuition that if we ask questions about a summary and its source, we will receive similar answers if the summary is factually consistent with the source. To evaluate QAGS, we collect human judgments of factual consistency on model-generated summaries for the CNN/DailyMail (Hermann et al., 2015) and XSUM (Narayan et al., 2018) summarization datasets. QAGS has substantially higher correlations with these judgments than other automatic evaluation metrics. Also, QAGS offers a natural form of interpretability: The answers and questions generated while computing QAGS indicate which tokens of a summary are inconsistent and why. We believe QAGS is a promising tool in automatically generating usable and factually consistent text. Code for QAGS will be available at https://github.com/W4ngatang/qags.

The Neural Covidex is a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset (CORD-19) curated by the Allen Institute for AI. It exists as part of a suite of tools we have developed to help domain experts tackle the ongoing global pandemic. We hope that improved information access capabilities to the scientific literature can inform evidence-based decision making and insight generation.

Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation. However, training non-monotonic models brings a new complication: how to search for a good ordering when there is a combinatorial explosion of orderings arriving at the same final result? Also, how do these automatic orderings compare with the actual behaviour of human translators? Current models rely on manually built biases or are left to explore all possibilities on their own. In this paper, we analyze the orderings produced by human post-editors and use them to train an automatic post-editing system. We compare the resulting system with those trained with left-to-right and random post-editing orderings. We observe that humans tend to follow a nearly left-to-right order, but with interesting deviations, such as preferring to start by correcting punctuation or verbs.

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate sequence-to-sequence models using conditional log-likelihood on a test set. However, the goal of sequence-to-sequence generation (or structured prediction) is to find the best output yˆ given an input x, and each task has its own downstream metric R that scores a model output by comparing against a set of references y*: R(yˆ, y* | x). While we hope that a model that excels in density estimation also performs well on the downstream metric, the exact correlation has not been studied for sequence generation tasks. In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared. First, log-likelihood is highly correlated with BLEU when we consider models within the same family (e.g. autoregressive models, or latent variable models with the same parameterization of the prior). However, we observe no correlation between rankings of models across different families: (1) among non-autoregressive latent variable models, a flexible prior distribution is better at density estimation but gives worse generation quality than a simple prior, and (2) autoregressive models offer the best translation performance overall, while latent variable models with a normalizing flow prior give the highest held-out log-likelihood across all datasets. Therefore, we recommend using a simple prior for the latent variable non-autoregressive model when fast generation speed is desired.

We seek to maximally use various data sources, such as parallel and monolingual data, to build an effective and efficient document-level translation system. In particular, we start by considering a noisy channel approach (CITATION) that combines a target-to-source translation model and a language model. By applying Bayes’ rule strategically, we reformulate this approach as a log-linear combination of translation, sentence-level and document-level language model probabilities. In addition to using static coefficients for each term, this formulation alternatively allows for the learning of dynamic per-token weights to more finely control the impact of the language models. Using both static or dynamic coefficients leads to improvements over a context-agnostic baseline and a context-aware concatenation model.

Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.

We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et al., 2020), we train an inference network to approximate the gradient of the marginal log probability of the target sentence, using the latent variable instead. This allows us to use gradient-based optimization to find the target sentence at inference time that approximately maximizes its marginal probability. As each refinement step only involves computation in the latent space of low dimensionality (we use 8 in our experiments), we avoid computational overhead incurred by existing non-autoregressive inference procedures that often refine in token space. We compare our approach to a recently proposed EM-like inference procedure (Shu et al., 2020) that optimizes in a hybrid space, consisting of both discrete and continuous variables. We evaluate our approach on WMT’14 En→De, WMT’16 Ro→En and IWSLT’16 De→En, and observe two advantages over the EM-like inference: (1) it is computationally efficient, i.e. each refinement step is twice as fast, and (2) it is more effective, resulting in higher marginal probabilities and BLEU scores with the same number of refinement steps. On WMT’14 En→De, for instance, our approach is able to decode 6.2 times faster than the autoregressive model with minimal degradation to translation quality (0.9 BLEU).

Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. However, in natural language, it is difficult to generate new examples that stay on the underlying data manifold. We introduce SSMBA, a data augmentation method for generating synthetic training examples by using a pair of corruption and reconstruction functions to move randomly on a data manifold. We investigate the use of SSMBA in the natural language domain, leveraging the manifold assumption to reconstruct corrupted text with masked language models. In experiments on robustness benchmarks across 3 tasks and 9 datasets, SSMBA consistently outperforms existing data augmentation methods and baseline models on both in-domain and OOD data, achieving gains of 0.8% on OOD Amazon reviews, 1.8% accuracy on OOD MNLI, and 1.4 BLEU on in-domain IWSLT14 German-English.

Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving infinite-length sequences from a recurrent language model when using common decoding algorithms. To analyze this issue, we first define inconsistency of a decoding algorithm, meaning that the algorithm can yield an infinite-length sequence that has zero probability under the model. We prove that commonly used incomplete decoding algorithms – greedy search, beam search, top-k sampling, and nucleus sampling – are inconsistent, despite the fact that recurrent language models are trained to produce sequences of finite length. Based on these insights, we propose two remedies which address inconsistency: consistent variants of top-k and nucleus sampling, and a self-terminating recurrent language model. Empirical results show that inconsistency occurs in practice, and that the proposed methods prevent inconsistency.

We aim to improve question answering (QA) by decomposing hard questions into simpler sub-questions that existing QA systems are capable of answering. Since labeling questions with decompositions is cumbersome, we take an unsupervised approach to produce sub-questions, also enabling us to leverage millions of questions from the internet. Specifically, we propose an algorithm for One-to-N Unsupervised Sequence transduction (ONUS) that learns to map one hard, multi-hop question to many simpler, single-hop sub-questions. We answer sub-questions with an off-the-shelf QA model and give the resulting answers to a recomposition model that combines them into a final answer. We show large QA improvements on HotpotQA over a strong baseline on the original, out-of-domain, and multi-hop dev sets. ONUS automatically learns to decompose different kinds of questions, while matching the utility of supervised and heuristic decomposition methods for QA and exceeding those methods in fluency. Qualitatively, we find that using sub-questions is promising for shedding light on why a QA system makes a prediction.

The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress towards more general and versatile NLP methods that learn from and for many tasks. Adapters—small learnt bottleneck layers inserted within each layer of a pre-trained model— ameliorate this issue by avoiding full fine-tuning of the entire model. However, sharing and integrating adapter layers is not straightforward. We propose AdapterHub, a framework that allows dynamic “stiching-in” of pre-trained adapters for different tasks and languages. The framework, built on top of the popular HuggingFace Transformers library, enables extremely easy and quick adaptations of state-of-the-art pre-trained models (e.g., BERT, RoBERTa, XLM-R) across tasks and languages. Downloading, sharing, and training adapters is as seamless as possible using minimal changes to the training scripts and a specialized infrastructure. Our framework enables scalable and easy access to sharing of task-specific models, particularly in low-resource scenarios. AdapterHub includes all recent adapter architectures and can be found at AdapterHub.ml

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot. In this work, we address the degeneracy problem due to capturing spurious correlations by quantitatively analyzing the mutual information between language IDs of the source and decoded sentences. Inspired by this analysis, we propose to use two simple but effective approaches: (1) decoder pre-training; (2) back-translation. These methods show significant improvement (4 22 BLEU points) over the vanilla zero-shot translation on three challenging multilingual datasets, and achieve similar or better results than the pivot-based approach.

Users of machine translation systems may desire to obtain multiple candidates translated in different ways. In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation. We describe two methods to extract the codes, either with or without the help of syntax information. For diverse generation, we sample multiple candidates, each of which conditioned on a unique code. Experiments show that the sampled translations have much higher diversity scores when using reasonable sentence codes, where the translation quality is still on par with the baselines even under strong constraint imposed by the codes. In qualitative analysis, we show that our method is able to generate paraphrase translations with drastically different structures. The proposed approach can be easily adopted to existing translation systems as no modification to the model is required.

Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We propose a method which demonstrates that a model trained on Dialogue NLI can be used to improve the consistency of a dialogue model, and evaluate the method with human evaluation and with automatic metrics on a suite of evaluation sets designed to measure a dialogue model’s consistency.

Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal. In this work, we propose a novel decoding algorithm— InDIGO—which supports flexible sequence generation in arbitrary orders through insertion operations. We extend Transformer, a state-of-the-art sequence generation model, to efficiently implement the proposed approach, enabling it to be trained with either a pre-defined generation order or adaptive orders obtained from beam-search. Experiments on four real-world tasks, including word order recovery, machine translation, image caption, and code generation, demonstrate that our algorithm can generate sequences following arbitrary orders, while achieving competitive or even better performance compared with the conventional left-to-right generation. The generated sequences show that InDIGO adopts adaptive generation orders based on input information.

We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. We train evidence agents to select the passage sentences that most convince a pretrained QA model of a given answer, if the QA model received those sentences instead of the full passage. Rather than finding evidence that convinces one model alone, we find that agents select evidence that generalizes; agent-chosen evidence increases the plausibility of the supported answer, as judged by other QA models and humans. Given its general nature, this approach improves QA in a robust manner: using agent-selected evidence (i) humans can correctly answer questions with only ~20% of the full passage and (ii) QA models can generalize to longer passages and harder questions.

Development sets are impractical to obtain for real low-resource languages, since using all available data for training is often more effective. However, development sets are widely used in research papers that purport to deal with low-resource natural language processing (NLP). Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages? And does it lead to overestimation or underestimation of performance? We repeat multiple experiments from recent work on neural models for low-resource NLP and compare results for models obtained by training with and without development sets. On average over languages, absolute accuracy differs by up to 1.4%. However, for some languages and tasks, differences are as big as 18.0% accuracy. Our results highlight the importance of realistic experimental setups in the publication of low-resource NLP research results.

We describe a multi-agent communication framework for examining high-level linguistic phenomena at the community-level. We demonstrate that complex linguistic behavior observed in natural language can be reproduced in this simple setting: i) the outcome of contact between communities is a function of inter- and intra-group connectivity; ii) linguistic contact either converges to the majority protocol, or in balanced cases leads to novel creole languages of lower complexity; and iii) a linguistic continuum emerges where neighboring languages are more mutually intelligible than farther removed languages. We conclude that at least some of the intricate properties of language evolution need not depend on complex evolved linguistic capabilities, but can emerge from simple social exchanges between perceptually-enabled agents playing communication games.

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental language drift: when a non-linguistic reward is used in a goal-based task, e.g. some scalar success metric, the communication protocol may easily and radically diverge from natural language. We recast translation as a multi-agent communication game and examine auxiliary training constraints for their effectiveness in mitigating language drift. We show that a combination of syntactic (language model likelihood) and semantic (visual grounding) constraints gives the best communication performance, allowing pre-trained agents to retain English syntax while learning to accurately convey the intended meaning.

Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results. However, earlier work on unsupervised parsing shows large performance differences between non-neural models trained on corpora in different languages, even for comparable amounts of data. With that in mind, we train instances of the PRPN architecture (Shen et al., 2018)—one of these unsupervised neural network parsers—for Arabic, Chinese, English, and German. We find that (i) the model strongly outperforms trivial baselines and, thus, acquires at least some parsing ability for all languages; (ii) good hyperparameter values seem to be universal; (iii) how the model benefits from larger training set sizes depends on the corpus, with the model achieving the largest performance gains when increasing the number of sentences from 2,500 to 12,500 for English. In addition, we show that, by sharing parameters between the related languages German and English, we can improve the model’s unsupervised parsing F1 score by up to 4% in the low-resource setting.

We show that BERT (Devlin et al., 2018) is a Markov random field language model. This formulation gives way to a natural procedure to sample sentences from BERT. We generate from BERT and find that it can produce high quality, fluent generations. Compared to the generations of a traditional left-to-right language model, BERT generates sentences that are more diverse but of slightly worse quality.

Standard sequential generation methods assume a pre-specified generation order, such as text generation methods which generate words from left to right. In this work, we propose a framework for training models of text generation that operate in non-monotonic orders; the model directly learns good orders, without any additional annotation. Our framework operates by generating a word at an arbitrary position, and then recursively generating words to its left and then words to its right, yielding a binary tree. Learning is framed as imitation learning, including a coaching method which moves from imitating an oracle to reinforcing the policy’s own preferences. Experimental results demonstrate that using the proposed method, it is possible to learn policies which generate text without pre-specifying a generation order while achieving competitive performance with conventional left-to-right generation.

We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses. We evaluate these strategies in realistic full conversations with humans and propose a model-based Bayesian calibration to address annotator bias. These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity. Our experiments reveal that better search algorithms lead to higher rated conversations. However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question.

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The proposed transition-based method successfully parses near the state of the art on both projective and non-projective languages, without assuming a certain parsing order.

In recent years, there have been amazing advances in deep learning methods for machine reading. In machine reading, the machine reader has to extract the answer from the given ground truth paragraph. Recently, the state-of-the-art machine reading models achieve human level performance in SQuAD which is a reading comprehension-style question answering (QA) task. The success of machine reading has inspired researchers to combine Information Retrieval with machine reading to tackle open-domain QA. However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question. In this study, we propose two neural network rankers that assign scores to different passages based on their likelihood of containing the answer to a given question. Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.

Most previous supervised event extraction methods have relied on features derived from manual annotations, and thus cannot be applied to new event types without extra annotation effort. We take a fresh look at event extraction and model it as a generic grounding problem: mapping each event mention to a specific type in a target event ontology. We design a transferable architecture of structural and compositional neural networks to jointly represent and map event mentions and types into a shared semantic space. Based on this new framework, we can select, for each event mention, the event type which is semantically closest in this space as its type. By leveraging manual annotations available for a small set of existing event types, our framework can be applied to new unseen event types without additional manual annotations. When tested on 23 unseen event types, our zero-shot framework, without manual annotations, achieved performance comparable to a supervised model trained from 3,000 sentences annotated with 500 event mentions.

While systems using the Neural Network-based Machine Translation (NMT) paradigm achieve the highest scores on recent shared tasks, phrase-based (PBMT) systems, rule-based (RBMT) systems and other systems may get better results for individual examples. Therefore, combined systems should achieve the best results for MT, particularly if the system combination method can take advantage of the strengths of each paradigm. In this paper, we describe a system that predicts whether a NMT, PBMT or RBMT will get the best Spanish translation result for a particular English sentence in DGT-TM 20161. Then we use fuzzy-match repair (FMR) as a mechanism to show that the combined system outperforms individual systems in a black-box machine translation setting.

We describe our work for the CALCS 2018 shared task on named entity recognition on code-switched data. Our system ranked first place for MS Arabic-Egyptian named entity recognition and third place for English-Spanish.

Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple commands paired with action sequences and is intended to test the strong generalization abilities of recurrent sequence-to-sequence models. Their initial experiments suggested that such models may fail because they lack the ability to extract systematic rules. Here, we take a closer look at SCAN and show that it does not always capture the kind of generalization that it was designed for. To mitigate this we propose a complementary dataset, which requires mapping actions back to the original commands, called NACS. We show that models that do well on SCAN do not necessarily do well on NACS, and that NACS exhibits properties more closely aligned with realistic use-cases for sequence-to-sequence models.

Grammar induction is the task of learning syntactic structure without the expert-labeled treebanks (Charniak and Carroll, 1992; Klein and Manning, 2002). Recent work on latent tree learning offers a new family of approaches to this problem by inducing syntactic structure using the supervision from a downstream NLP task (Yogatama et al., 2017; Maillard et al., 2017; Choi et al., 2018). In a recent paper published at ICLR, Shen et al. (2018) introduce such a model and report near state-of-the-art results on the target task of language modeling, and the first strong latent tree learning result on constituency parsing. During the analysis of this model, we discover issues that make the original results hard to trust, including tuning and even training on what is effectively the test set. Here, we analyze the model under different configurations to understand what it learns and to identify the conditions under which it succeeds. We find that this model represents the first empirical success for neural network latent tree learning, and that neural language modeling warrants further study as a setting for grammar induction.

We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space via which all available resources and knowledge can be shared across multiple languages. Beyond word alignment, we introduce multiple cluster-level alignments and enforce the word clusters to be consistently distributed across multiple languages. We exploit three signals for clustering: (1) neighbor words in the monolingual word embedding space; (2) character-level information; and (3) linguistic properties (e.g., apposition, locative suffix) derived from linguistic structure knowledge bases available for thousands of languages. We introduce a new cluster-consistent correlational neural network to construct the common semantic space by aligning words as well as clusters. Intrinsic evaluation on monolingual and multilingual QVEC tasks shows our approach achieves significantly higher correlation with linguistic features which are extracted from manually crafted lexical resources than state-of-the-art multi-lingual embedding learning methods do. Using low-resource language name tagging as a case study for extrinsic evaluation, our approach achieves up to 14.6% absolute F-score gain over the state of the art on cross-lingual direct transfer. Our approach is also shown to be robust even when the size of bilingual dictionary is small.

Beam search is a widely used approximate search strategy for neural network decoders, and it generally outperforms simple greedy decoding on tasks like machine translation. However, this improvement comes at substantial computational cost. In this paper, we propose a flexible new method that allows us to reap nearly the full benefits of beam search with nearly no additional computational cost. The method revolves around a small neural network actor that is trained to observe and manipulate the hidden state of a previously-trained decoder. To train this actor network, we introduce the use of a pseudo-parallel corpus built using the output of beam search on a base model, ranked by a target quality metric like BLEU. Our method is inspired by earlier work on this problem, but requires no reinforcement learning, and can be trained reliably on a range of models. Experiments on three parallel corpora and three architectures show that the method yields substantial improvements in translation quality and speed over each base system.

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine translation (En-De and En-Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic meta-embeddings, a simple yet effective method for the supervised learning of embedding ensembles, which leads to state-of-the-art performance within the same model class on a variety of tasks. We subsequently show how the technique can be used to shed new light on the usage of word embeddings in NLP systems.

In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm (MAML, Finn, et al., 2017) for low-resource neural machine translation (NMT). We frame low-resource translation as a meta-learning problem where we learn to adapt to low-resource languages based on multilingual high-resource language tasks. We use the universal lexical representation (Gu et al., 2018b) to overcome the input-output mismatch across different languages. We evaluate the proposed meta-learning strategy using eighteen European languages (Bg, Cs, Da, De, El, Es, Et, Fr, Hu, It, Lt, Nl, Pl, Pt, Sk, Sl, Sv and Ru) as source tasks and five diverse languages (Ro,Lv, Fi, Tr and Ko) as target tasks. We show that the proposed approach significantly outperforms the multilingual, transfer learning based approach (Zoph et al., 2016) and enables us to train a competitive NMT system with only a fraction of training examples. For instance, the proposed approach can achieve as high as 22.04 BLEU on Romanian-English WMT’16 by seeing only 16,000 translated words (~600 parallel sentences)

Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty. We address these concerns with a model that incorporates document covariates to estimate conditional word embedding distributions. Our model allows for (a) hypothesis tests about the meanings of terms, (b) assessments as to whether a word is near or far from another conditioned on different covariate values, and (c) assessments as to whether estimated differences are statistically significant.

A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree structure. In a recent paper, Shen et al. (2018) introduce such a model and report near-state-of-the-art results on the target task of language modeling, and the first strong latent tree learning result on constituency parsing. In an attempt to reproduce these results, we discover issues that make the original results hard to trust, including tuning and even training on what is effectively the test set. Here, we attempt to reproduce these results in a fair experiment and to extend them to two new datasets. We find that the results of this work are robust: All variants of the model under study outperform all latent tree learning baselines, and perform competitively with symbolic grammar induction systems. We find that this model represents the first empirical success for latent tree learning, and that neural network language modeling warrants further study as a setting for grammar induction.

Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned. We train this neural network with reinforcement learning. The actions correspond to selecting terms to build a reformulated query, and the reward is the document recall. We evaluate our approach on three datasets against strong baselines and show a relative improvement of 5-20% in terms of recall. Furthermore, we present a simple method to estimate a conservative upper-bound performance of a model in a particular environment and verify that there is still large room for improvements.

Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-to-end learning algorithms. The problem of decoding, however, has received relatively little attention from the research community. In this paper, we solely focus on the problem of decoding given a trained neural machine translation model. Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding objective. More specifically, we design an actor that observes and manipulates the hidden state of the neural machine translation decoder and propose to train it using a variant of deterministic policy gradient. We extensively evaluate the proposed algorithm using four language pairs and two decoding objectives and show that we can indeed train a trainable greedy decoder that generates a better translation (in terms of a target decoding objective) with minimal computational overhead.

Translating in real-time, a.k.a.simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.

We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and has been used to train systems for production environments.

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT’15 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of the BLEU score and human judgment.

In this paper we present our systems for the DiscoMT 2017 cross-lingual pronoun prediction shared task. For all four language pairs, we trained a standard attention-based neural machine translation system as well as three variants that incorporate information from the preceding source sentence. We show that our systems, which are not specifically designed for pronoun prediction and may be used to generate complete sentence translations, generally achieve competitive results on this task.

This paper describes a builder entry, named “strawman”, to the sentence-level sentiment analysis task of the “Build It, Break It” shared task of the First Workshop on Building Linguistically Generalizable NLP Systems. The goal of a builder is to provide an automated sentiment analyzer that would serve as a target for breakers whose goal is to find pairs of minimally-differing sentences that break the analyzer.

There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a hybrid model, called NMT+RNNG, that learns to parse and translate by combining the recurrent neural network grammar into the attention-based neural machine translation. Our approach encourages the neural machine translation model to incorporate linguistic prior during training, and lets it translate on its own afterward. Extensive experiments with four language pairs show the effectiveness of the proposed NMT+RNNG.

Distributional models that learn rich semantic word representations are a success story of recent NLP research. However, developing models that learn useful representations of phrases and sentences has proved far harder. We propose using the definitions found in everyday dictionaries as a means of bridging this gap between lexical and phrasal semantics. Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions. We present two applications of these architectures: reverse dictionaries that return the name of a concept given a definition or description and general-knowledge crossword question answerers. On both tasks, neural language embedding models trained on definitions from a handful of freely-available lexical resources perform as well or better than existing commercial systems that rely on significant task-specific engineering. The results highlight the effectiveness of both neural embedding architectures and definition-based training for developing models that understand phrases and sentences.

Interlingua based Machine Translation (MT) aims to encode multiple languages into a common linguistic representation and then decode sentences in multiple target languages from this representation. In this work we explore this idea in the context of neural encoder decoder architectures, albeit on a smaller scale and without MT as the end goal. Specifically, we consider the case of three languages or modalities X, Z and Y wherein we are interested in generating sequences in Y starting from information available in X. However, there is no parallel training data available between X and Y but, training data is available between X & Z and Z & Y (as is often the case in many real world applications). Z thus acts as a pivot/bridge. An obvious solution, which is perhaps less elegant but works very well in practice is to train a two stage model which first converts from X to Z and then from Z to Y. Instead we explore an interlingua inspired solution which jointly learns to do the following (i) encode X and Z to a common representation and (ii) decode Y from this common representation. We evaluate our model on two tasks: (i) bridge transliteration and (ii) bridge captioning. We report promising results in both these applications and believe that this is a right step towards truly interlingua inspired encoder decoder architectures.

Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Despite being relatively new (Kalchbrenner and Blunsom, 2013; Cho et al., 2014; Sutskever et al., 2014), NMT has already shown promising results, achieving state-of-the-art performances for various language pairs (Luong et al, 2015a; Jean et al, 2015; Luong et al, 2015b; Sennrich et al., 2016; Luong and Manning, 2016). While many of these NMT papers were presented to the ACL community, research and practice of NMT are only at their beginning stage. This tutorial would be a great opportunity for the whole community of machine translation and natural language processing to learn more about a very promising new approach to MT. This tutorial has four parts.In the first part, we start with an overview of MT approaches, including: (a) traditional methods that have been dominant over the past twenty years and (b) recent hybrid models with the use of neural network components. From these, we motivate why an end-to-end approach like neural machine translation is needed. The second part introduces a basic instance of NMT. We start out with a discussion of recurrent neural networks, including the back-propagation-through-time algorithm and stochastic gradient descent optimizers, as these are the foundation on which NMT builds. We then describe in detail the basic sequence-to-sequence architecture of NMT (Cho et al., 2014; Sutskever et al., 2014), the maximum likelihood training approach, and a simple beam-search decoder to produce translations.The third part of our tutorial describes techniques to build state-of-the-art NMT. We start with approaches to extend the vocabulary coverage of NMT (Luong et al., 2015a; Jean et al., 2015; Chitnis and DeNero, 2015). We then introduce the idea of jointly learning both translations and alignments through an attention mechanism (Bahdanau et al., 2015); other variants of attention (Luong et al., 2015b; Tu et al., 2016) are discussed too. We describe a recent trend in NMT, that is to translate at the sub-word level (Chung et al., 2016; Luong and Manning, 2016; Sennrich et al., 2016), so that language variations can be effectively handled. We then give tips on training and testing NMT systems such as batching and ensembling. In the final part of the tutorial, we briefly describe promising approaches, such as (a) how to combine multiple tasks to help translation (Dong et al., 2015; Luong et al., 2016; Firat et al., 2016; Zoph and Knight, 2016) and (b) how to utilize monolingual corpora (Sennrich et al., 2016). Lastly, we conclude with challenges remained to be solved for future NMT.PS: we would also like to acknowledge the very first paper by Forcada and Ñeco (1997) on sequence-to-sequence models for translation!