Marjan Ghazvininejad


2023

pdf bib
In-context Examples Selection for Machine Translation
Sweta Agrawal | Chunting Zhou | Mike Lewis | Luke Zettlemoyer | Marjan Ghazvininejad
Findings of the Association for Computational Linguistics: ACL 2023

Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation (MT), these examples are typically randomly sampled from the development dataset with a similar distribution as the evaluation set. However, it is unclear how the choice of these in context examples and their ordering impacts the output translation quality. In this work, we aim to understand the properties of good in-context examples for MT in both in-domain and out-of-domain settings. We show that the translation quality and the domain of the in-context examples matter and that 1-shot noisy unrelated examples can have a catastrophic impact on output quality. While concatenating multiple random examples reduces the effect of noise, a single good prompt optimized to maximize translation quality on the development dataset can elicit learned information from the pre-trained language model. Adding similar examples based on an n-gram overlap with the test source significantly and consistently improves the translation quality of the outputs, outperforming a strong kNN-MT baseline in 2 out of 4 out-of-domain datasets.

pdf bib
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Davis Liang | Hila Gonen | Yuning Mao | Rui Hou | Naman Goyal | Marjan Ghazvininejad | Luke Zettlemoyer | Madian Khabsa
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Large multilingual language models typically rely on a single vocabulary shared across 100+ languages. As these models have increased in parameter count and depth, vocabulary size has remained largely unchanged. This vocabulary bottleneck limits the representational capabilities of multilingual models like XLM-R. In this paper, we introduce a new approach for scaling to very large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language. Tokenizations using our vocabulary are typically more semantically meaningful and shorter compared to XLM-R. Leveraging this improved vocabulary, we train XLM-V, a multilingual language model with a one million token vocabulary. XLM-V outperforms XLM-R on every task we tested on ranging from natural language inference (XNLI), question answering (MLQA, XQuAD, TyDiQA), to named entity recognition (WikiAnn). XLM-V is particularly effective on low-resource language tasks and outperforms XLM-R by 11.2% and 5.8% absolute on MasakhaNER and Americas NLI, respectively.

2022

pdf bib
BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation
Eleftheria Briakou | Sida Wang | Luke Zettlemoyer | Marjan Ghazvininejad
Findings of the Association for Computational Linguistics: NAACL 2022

Mined bitexts can contain imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT). While filtering such pairs out is known to improve final model quality, we argue that it is suboptimal in low-resource conditions where even mined data can be limited. In our work, we propose instead, to refine the mined bitexts via automatic editing: given a sentence in a language xf, and a possibly imperfect translation of it xe, our model generates a revised version xf' or xe' that yields a more equivalent translation pair (i.e., <xf, xe'> or <xf', xe>). We use a simple editing strategy by (1) mining potentially imperfect translations for each sentence in a given bitext, (2) learning a model to reconstruct the original translations and translate, in a multi-task fashion. Experiments demonstrate that our approach successfully improves the quality of CCMatrix mined bitext for 5 low-resource language-pairs and 10 translation directions by up to 8 BLEU points, in most cases improving upon a competitive translation-based baseline.

pdf bib
Natural Language to Code Translation with Execution
Freda Shi | Daniel Fried | Marjan Ghazvininejad | Luke Zettlemoyer | Sida I. Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter alia). While these models do not explicitly incorporate program semantics (i.e., execution results) during training, they are able to generate correct solutions for many problems. However, choosing a single correct program from a generated set for each problem remains challenging. In this work, we introduce execution result–based minimum Bayes risk decoding (MBR-EXEC) for program selection and show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks. We select output programs from a generated candidate set by marginalizing over program implementations that share the same semantics. Because exact equivalence is intractable, we execute each program on a small number of test inputs to approximate semantic equivalence. Across datasets, execution or simulated execution significantly outperforms the methods that do not involve program semantics. We find that MBR-EXEC consistently improves over all execution-unaware selection methods, suggesting it as an effective approach for natural language to code translation.

pdf bib
Discourse-Aware Soft Prompting for Text Generation
Marjan Ghazvininejad | Vladimir Karpukhin | Vera Gor | Asli Celikyilmaz
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Current efficient fine-tuning methods(e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While showing strong performance on some generation tasks, they don’t generalize across all generation tasks. We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text. We investigate two design choices: First, we apply hierarchical blocking on the prefix parameters to simulate a higher-level discourse structure of human written text. Second, we apply attention sparsity on the prefix parameters at different layers of the network and learn sparse transformations on the softmax-function. We show that structured design of prefix parameters yields more coherent, faithful and relevant generations than the baseline prefix-tuning on all generation tasks.

2021

pdf bib
Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
Asa Cooper Stickland | Xian Li | Marjan Ghazvininejad
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

There has been recent success in pre-training on monolingual data and fine-tuning on Machine Translation (MT), but it remains unclear how to best leverage a pre-trained model for a given MT task. This paper investigates the benefits and drawbacks of freezing parameters, and adding new ones, when fine-tuning a pre-trained model on MT. We focus on 1) Fine-tuning a model trained only on English monolingual data, BART. 2) Fine-tuning a model trained on monolingual data from 25 languages, mBART. For BART we get the best performance by freezing most of the model parameters, and adding extra positional embeddings. For mBART we match or outperform the performance of naive fine-tuning for most language pairs with the encoder, and most of the decoder, frozen. The encoder-decoder attention parameters are most important to fine-tune. When constraining ourselves to an out-of-domain training set for Vietnamese to English we see the largest improvements over the fine-tuning baseline.

pdf bib
Detecting Hallucinated Content in Conditional Neural Sequence Generation
Chunting Zhou | Graham Neubig | Jiatao Gu | Mona Diab | Francisco Guzmán | Luke Zettlemoyer | Marjan Ghazvininejad
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Bhargavi Paranjape | Julian Michael | Marjan Ghazvininejad | Hannaneh Hajishirzi | Luke Zettlemoyer
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Distributionally Robust Multilingual Machine Translation
Chunting Zhou | Daniel Levy | Xian Li | Marjan Ghazvininejad | Graham Neubig
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.

pdf bib
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation
Alexander Fabbri | Simeng Han | Haoyuan Li | Haoran Li | Marjan Ghazvininejad | Shafiq Joty | Dragomir Radev | Yashar Mehdad
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. However, these models are typically fine-tuned on hundreds of thousands of data points, an infeasible requirement when applying summarization to new, niche domains. In this work, we introduce a novel and generalizable method, called WikiTransfer, for fine-tuning pretrained models for summarization in an unsupervised, dataset-specific manner. WikiTransfer fine-tunes pretrained models on pseudo-summaries, produced from generic Wikipedia data, which contain characteristics of the target dataset, such as the length and level of abstraction of the desired summaries. WikiTransfer models achieve state-of-the-art, zero-shot abstractive summarization performance on the CNN-DailyMail dataset and demonstrate the effectiveness of our approach on three additional diverse datasets. These models are more robust to noisy data and also achieve better or comparable few-shot performance using 10 and 100 training examples when compared to few-shot transfer from other summarization datasets. To further boost performance, we employ data augmentation via round-trip translation as well as introduce a regularization term for improved few-shot transfer. To understand the role of dataset aspects in transfer performance and the quality of the resulting output summaries, we further study the effect of the components of our unsupervised fine-tuning data and analyze few-shot performance using both automatic and human evaluation.

pdf bib
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog
Arun Babu | Akshat Shrivastava | Armen Aghajanyan | Ahmed Aly | Angela Fan | Marjan Ghazvininejad
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-time conversational use cases has been stymied by higher compute requirements and thus higher latency. In this work, we propose a non-autoregressive approach to predict semantic parse trees with an efficient seq2seq model architecture. By combining non-autoregressive prediction with convolutional neural networks, we achieve significant latency gains and parameter size reduction compared to traditional RNN models. Our novel architecture achieves up to an 81% reduction in latency on TOP dataset and retains competitive performance to non-pretrained models on three different semantic parsing datasets.

pdf bib
EASE: Extractive-Abstractive Summarization End-to-End using the Information Bottleneck Principle
Haoran Li | Arash Einolghozati | Srinivasan Iyer | Bhargavi Paranjape | Yashar Mehdad | Sonal Gupta | Marjan Ghazvininejad
Proceedings of the Third Workshop on New Frontiers in Summarization

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. Extractive summarization systems, though interpretable, suffer from redundancy and possible lack of coherence. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary. Our framework can be applied to any evidence-based text generation problem and can accommodate various pretrained models in its simple architecture. We use the Information Bottleneck principle to jointly train the extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans and then generates a summary using only the evidence. Using automatic and human evaluations, we show that the generated summaries are better than strong extractive and extractive-abstractive baselines.

2020

pdf bib
Multilingual Denoising Pre-training for Neural Machine Translation
Yinhan Liu | Jiatao Gu | Naman Goyal | Xian Li | Sergey Edunov | Marjan Ghazvininejad | Mike Lewis | Luke Zettlemoyer
Transactions of the Association for Computational Linguistics, Volume 8

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART—a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective (Lewis et al., 2019). mBART is the first method for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, whereas previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine-tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task- specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show that it enables transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to effective pre-training.1

pdf bib
Simple and Effective Retrieve-Edit-Rerank Text Generation
Nabil Hossain | Marjan Ghazvininejad | Luke Zettlemoyer
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Retrieve-and-edit seq2seq methods typically retrieve an output from the training set and learn a model to edit it to produce the final output. We propose to extend this framework with a simple and effective post-generation ranking approach. Our framework (i) retrieves several potentially relevant outputs for each input, (ii) edits each candidate independently, and (iii) re-ranks the edited candidates to select the final output. We use a standard editing model with simple task-specific re-ranking approaches, and we show empirically that this approach outperforms existing, significantly more complex methodologies. Experiments on two machine translation (MT) datasets show new state-of-art results. We also achieve near state-of-art performance on the Gigaword summarization dataset, where our analyses show that there is significant room for performance improvement with better candidate output selection in future work.

pdf bib
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Mike Lewis | Yinhan Liu | Naman Goyal | Marjan Ghazvininejad | Abdelrahman Mohamed | Omer Levy | Veselin Stoyanov | Luke Zettlemoyer
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simplicity, can be seen as generalizing BERT (due to the bidirectional encoder), GPT (with the left-to-right decoder), and other recent pretraining schemes. We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token. BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa on GLUE and SQuAD, and achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 3.5 ROUGE. BART also provides a 1.1 BLEU increase over a back-translation system for machine translation, with only target language pretraining. We also replicate other pretraining schemes within the BART framework, to understand their effect on end-task performance.

2019

pdf bib
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
Nima Pourdamghani | Nada Aldarrab | Marjan Ghazvininejad | Kevin Knight | Jonathan May
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation into a two step process: generating a rough gloss by means of a dictionary and then ‘translating’ the resulting pseudo-translation, or ‘Translationese’ into a fully fluent translation. We build our Translationese decoder once from a mish-mash of parallel data that has the target language in common and then can build dictionaries on demand using unsupervised techniques, resulting in rapidly generated unsupervised neural MT systems for many source languages. We apply this process to 14 test languages, obtaining better or comparable translation results on high-resource languages than previously published unsupervised MT studies, and obtaining good quality results for low-resource languages that have never been used in an unsupervised MT scenario.

pdf bib
Mask-Predict: Parallel Decoding of Conditional Masked Language Models
Marjan Ghazvininejad | Omer Levy | Yinhan Liu | Luke Zettlemoyer
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation. This approach allows for efficient iterative decoding, where we first predict all of the target words non-autoregressively, and then repeatedly mask out and regenerate the subset of words that the model is least confident about. By applying this strategy for a constant number of iterations, our model improves state-of-the-art performance levels for non-autoregressive and parallel decoding translation models by over 4 BLEU on average. It is also able to reach within about 1 BLEU point of a typical left-to-right transformer model, while decoding significantly faster.

pdf bib
Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation
Vladimir Karpukhin | Omer Levy | Jacob Eisenstein | Marjan Ghazvininejad
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

Contemporary machine translation systems achieve greater coverage by applying subword models such as BPE and character-level CNNs, but these methods are highly sensitive to orthographical variations such as spelling mistakes. We show how training on a mild amount of random synthetic noise can dramatically improve robustness to these variations, without diminishing performance on clean text. We focus on translation performance on natural typos, and show that robustness to such noise can be achieved using a balanced diet of simple synthetic noises at training time, without access to the natural noise data or distribution.

pdf bib
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
Antoine Bosselut | Asli Celikyilmaz | Marjan Ghazvininejad | Srinivasan Iyer | Urvashi Khandelwal | Hannah Rashkin | Thomas Wolf
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation

2018

pdf bib
Towards Controllable Story Generation
Nanyun Peng | Marjan Ghazvininejad | Jonathan May | Kevin Knight
Proceedings of the First Workshop on Storytelling

We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.

pdf bib
Neural Poetry Translation
Marjan Ghazvininejad | Yejin Choi | Kevin Knight
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

We present the first neural poetry translation system. Unlike previous works that often fail to produce any translation for fixed rhyme and rhythm patterns, our system always translates a source text to an English poem. Human evaluation of the translations ranks the quality as acceptable 78.2% of the time.

pdf bib
Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation
Nima Pourdamghani | Marjan Ghazvininejad | Kevin Knight
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

We present a method for improving word alignments using word similarities. This method is based on encouraging common alignment links between semantically similar words. We use word vectors trained on monolingual data to estimate similarity. Our experiments on translating fifteen languages into English show consistent BLEU score improvements across the languages.

2017

pdf bib
Hafez: an Interactive Poetry Generation System
Marjan Ghazvininejad | Xing Shi | Jay Priyadarshi | Kevin Knight
Proceedings of ACL 2017, System Demonstrations

2016

pdf bib
Generating Topical Poetry
Marjan Ghazvininejad | Xing Shi | Yejin Choi | Kevin Knight
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf bib
How Much Information Does a Human Translator Add to the Original?
Barret Zoph | Marjan Ghazvininejad | Kevin Knight
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
How to Memorize a Random 60-Bit String
Marjan Ghazvininejad | Kevin Knight
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies