Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.

As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rectify potential errors. The question arises naturally: can we use language feedback to align large language models (LLMs)? In contrast to previous research that aligns LLMs with scalar rewards, we present the first systematic exploration of alignment through the lens of language feedback (i.e., judgment). We start with an in-depth investigation of potential methods that can be adapted for aligning LLMs with judgments, revealing that these methods cannot fully capitalize on judgments. To facilitate more effective utilization of judgments, we propose a novel framework, Contrastive Unlikelihood Training (CUT), that allows for fine-grained inappropriate content detection and correction based on judgments. Our results show that, with merely 1317 off-the-shelf judgment data, CUT can beat the 175B DaVinci003 and surpass the best baseline by 50.84 points on AlpacaEval using LLaMA2-13b. CUT can also align LLMs in an iterative fashion using up-to-date model-specific judgments, improving performance from 81.09 to 91.68 points on AlpacaEval using LLaMA2-chat-13b. Further analysis suggests that judgments hold greater potential in LLM alignment than rewards.

In this work we propose a pragmatic method that reduces the annotation cost for structured label spaces using active learning. Our approach leverages partial annotation, which reduces labeling costs for structured outputs by selecting only the most informative sub-structures for annotation. We also utilize self-training to incorporate the current model’s automatic predictions as pseudo-labels for un-annotated sub-structures. A key challenge in effectively combining partial annotation with self-training to reduce annotation cost is determining which sub-structures to select to label. To address this challenge, we adopt an error estimator to adaptively decide the partial selection ratio according to the current model’s capability. In evaluations spanning four structured prediction tasks, we show that our combination of partial annotation and self-training using an adaptive selection ratio reduces annotation cost over strong full annotation baselines under a fair comparison scheme that takes reading time into consideration.

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an attractive alternative that allows outputting multiple tokens in a single generation step. Nevertheless, due to the incompatibility between absolute positional encoding and insertion-based generation schemes, it needs to refresh the encoding of every token in the generated partial hypothesis at each step, which could be costly. We design a novel reusable positional encoding scheme for Insertion Transformers called Fractional Positional Encoding (FPE), which allows reusing representations calculated in previous steps. Empirical studies on various text generation tasks demonstrate the effectiveness of FPE, which leads to floating-point operation reduction and latency improvements on batched decoding.

In this work, we investigate transfer learning from semantic role labeling (SRL) to event argument extraction (EAE), considering their similar argument structures. We view the extraction task as a role querying problem, unifying various methods into a single framework. There are key discrepancies on role labels and distant arguments between semantic role and event argument annotations. To mitigate these discrepancies, we specify natural language-like queries to tackle the label mismatch problem and devise argument augmentation to recover distant arguments. We show that SRL annotations can serve as a valuable resource for EAE, and a template-based slot querying strategy is especially effective for facilitating the transfer. In extensive evaluations on two English EAE benchmarks, our proposed model obtains impressive zero-shot results by leveraging SRL annotations, reaching nearly 80% of the fullysupervised scores. It further provides benefits in low-resource cases, where few EAE annotations are available. Moreover, we show that our approach generalizes to cross-domain and multilingual scenarios.

In this work, we provide a literature review of active learning (AL) for its applications in natural language processing (NLP). In addition to a fine-grained categorization of query strategies, we also investigate several other important aspects of applying AL to NLP problems. These include AL for structured prediction tasks, annotation cost, model learning (especially with deep neural models), and starting and stopping AL. Finally, we conclude with a discussion of related topics and future directions.

In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on popular benchmarks, the potential costs and benefits of structured decoding in these models have become less clear. With extensive experiments on PropBank SRL datasets, we find that more structured decoding methods outperform BIO-tagging when using static (word type) embeddings across all experimental settings. However, when used in conjunction with pre-trained contextualized word representations, the benefits are diminished. We also experiment in cross-genre and cross-lingual settings and find similar trends. We further perform speed comparisons and provide analysis on the accuracy-efficiency trade-offs among different decoding methods.

Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervised SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency- and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.

In this work, we explore the implicit event argument detection task, which studies event arguments beyond sentence boundaries. The addition of cross-sentence argument candidates imposes great challenges for modeling. To reduce the number of candidates, we adopt a two-step approach, decomposing the problem into two sub-problems: argument head-word detection and head-to-span expansion. Evaluated on the recent RAMS dataset (Ebner et al., 2020), our model achieves overall better performance than a strong sequence labeling baseline. We further provide detailed error analysis, presenting where the model mainly makes errors and indicating directions for future improvements. It remains a challenge to detect implicit arguments, calling for more future work of document-level modeling for this task.

Recently, pre-training contextualized encoders with language model (LM) objectives has been shown an effective semi-supervised method for structured prediction. In this work, we empirically explore an alternative pre-training method for contextualized encoders. Instead of predicting words in LMs, we “mask out” and predict word order information, with a local ordering strategy and word-selecting objectives. With evaluations on three typical structured prediction tasks (dependency parsing, POS tagging, and NER) over four languages (English, Finnish, Czech, and Italian), we show that our method is consistently beneficial. We further conduct detailed error analysis, including one that examines a specific type of parsing error where the head is misidentified. The results show that pre-trained contextual encoders can bring improvements in a structured way, suggesting that they may be able to capture higher-order patterns and feature combinations from unlabeled data.

In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among target outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the output pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM) (Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical results on five translation tasks show that compared with CMLM, our method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5x speedup. Further analysis indicates that our method reduces repeated translations and performs better at longer sentences. Our code will be released to the public.

Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance of natural language processing (NLP) on low-resource languages. However, given a particular task language, it is not clear which language to transfer from, and the standard strategy is to select languages based on ad hoc criteria, usually the intuition of the experimenter. Since a large number of features contribute to the success of cross-lingual transfer (including phylogenetic similarity, typological properties, lexical overlap, or size of available data), even the most enlightened experimenter rarely considers all these factors for the particular task at hand. In this paper, we consider this task of automatically selecting optimal transfer languages as a ranking problem, and build models that consider the aforementioned features to perform this prediction. In experiments on representative NLP tasks, we demonstrate that our model predicts good transfer languages much better than ad hoc baselines considering single features in isolation, and glean insights on what features are most informative for each different NLP tasks, which may inform future ad hoc selection even without use of our method.

Cross-lingual transfer is an effective way to build syntactic analysis tools in low-resource languages. However, transfer is difficult when transferring to typologically distant languages, especially when neither annotated target data nor parallel corpora are available. In this paper, we focus on methods for cross-lingual transfer to distant languages and propose to learn a generative model with a structured prior that utilizes labeled source data and unlabeled target data jointly. The parameters of source model and target model are softly shared through a regularized log likelihood objective. An invertible projection is employed to learn a new interlingual latent embedding space that compensates for imperfect cross-lingual word embedding input. We evaluate our method on two syntactic tasks: part-of-speech (POS) tagging and dependency parsing. On the Universal Dependency Treebanks, we use English as the only source corpus and transfer to a wide range of target languages. On the 10 languages in this dataset that are distant from English, our method yields an average of 5.2% absolute improvement on POS tagging and 8.3% absolute improvement on dependency parsing over a direct transfer method using state-of-the-art discriminative models.

In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that global output-structured models can generally obtain better performance, especially on the metric of sentence-level Complete Match. However, probably because neural models already learn good global views of the inputs, the improvement brought by structured output modeling is modest.

Cross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning language-agnostic representations, in the form of word embeddings or contextual encodings. In this work, we propose to leverage unannotated sentences from auxiliary languages to help learning language-agnostic representations. Specifically, we explore adversarial training for learning contextual encoders that produce invariant representations across languages to facilitate cross-lingual transfer. We conduct experiments on cross-lingual dependency parsing where we train a dependency parser on a source language and transfer it to a wide range of target languages. Experiments on 28 target languages demonstrate that adversarial training significantly improves the overall transfer performances under several different settings. We conduct a careful analysis to evaluate the language-agnostic representations resulted from adversarial training.

Different languages might have different word orders. In this paper, we investigate crosslingual transfer and posit that an orderagnostic model will perform better when transferring to distant foreign languages. To test our hypothesis, we train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages. Specifically, we compare encoders and decoders based on Recurrent Neural Networks (RNNs) and modified self-attentive architectures. The former relies on sequential information while the latter is more flexible at modeling word order. Rigorous experiments and detailed analysis shows that RNN-based architectures transfer well to languages that are close to English, while self-attentive models have better overall cross-lingual transferability and perform especially well on distant languages.

Quality estimation (QE) of machine translation (MT) systems is a task of growing importance. It reduces the cost of post-editing, allowing machine-translated text to be used in formal occasions. In this work, we describe our submission system in WMT 2019 sentence-level QE task. We mainly explore the utilization of pre-trained translation models in QE and adopt a bi-directional translation-like strategy. The strategy is similar to ELMo, but additionally conditions on source sentences. Experiments on WMT QE dataset show that our strategy, which makes the pre-training slightly harder, can bring improvements for QE. In WMT-2019 QE task, our system ranked in the second place on En-De NMT dataset and the third place on En-Ru NMT dataset.

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently no matter how similar they are. However, this might be inefficient since some partial hypotheses can contain only local differences that will not influence future predictions. In this work, we introduce recombination in NMT decoding based on the concept of the “equivalence” of partial hypotheses. Heuristically, we use a simple n-gram suffix based equivalence function and adapt it into beam search decoding. Through experiments on large-scale Chinese-to-English and English-to-Germen translation tasks, we show that the proposed method can obtain similar translation quality with a smaller beam size, making NMT decoding more efficient.

This paper describes the system for our participation in the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In this work, we design a system based on UDPipe1 for universal dependency parsing, where multilingual transition-based models are trained for different treebanks. Our system directly takes raw texts as input, performing several intermediate steps like tokenizing and tagging, and finally generates the corresponding dependency trees. For the special surprise languages for this task, we adopt a delexicalized strategy and predict basing on transfer learning from other related languages. In the final evaluation of the shared task, our system achieves a result of 66.53% in macro-averaged LAS F1-score.

Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark.

Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are computationally inefficient. In this paper, we propose a greedy neural word segmenter with balanced word and character embedding inputs to alleviate the existing drawbacks. Our segmenter is truly end-to-end, capable of performing segmentation much faster and even more accurate than state-of-the-art neural models on Chinese benchmark datasets.

For the task of implicit discourse relation recognition, traditional models utilizing manual features can suffer from data sparsity problem. Neural models provide a solution with distributed representations, which could encode the latent semantic information, and are suitable for recognizing semantic relations between argument pairs. However, conventional vector representations usually adopt embeddings at the word level and cannot well handle the rare word problem without carefully considering morphological information at character level. Moreover, embeddings are assigned to individual words independently, which lacks of the crucial contextual information. This paper proposes a neural model utilizing context-aware character-enhanced embeddings to alleviate the drawbacks of the current word level representation. Our experiments show that the enhanced embeddings work well and the proposed model obtains state-of-the-art results.