Veselin Stoyanov


pdf bib
Improving In-Context Few-Shot Learning via Self-Supervised Training
Mingda Chen | Jingfei Du | Ramakanth Pasunuru | Todor Mihaylov | Srini Iyer | Veselin Stoyanov | Zornitsa Kozareva
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Self-supervised pretraining has made few-shot learning possible for many NLP tasks. But the pretraining objectives are not typically adapted specifically for in-context few-shot learning. In this paper, we propose to use self-supervision in an intermediate training stage between pretraining and downstream few-shot usage with the goal to teach the model to perform in-context few shot learning. We propose and evaluate four self-supervised objectives on two benchmarks. We find that the intermediate self-supervision stage produces models that outperform strong baselines. Ablation study shows that several factors affect the downstream performance, such as the amount of training data and the diversity of the self-supervised objectives. Human-annotated cross-task supervision and self-supervision are complementary. Qualitative analysis suggests that the self-supervised-trained models are better at following task requirements.

pdf bib
Prompt-free and Efficient Few-shot Learning with Language Models
Rabeeh Karimi Mahabadi | Luke Zettlemoyer | James Henderson | Lambert Mathias | Marzieh Saeidi | Veselin Stoyanov | Majid Yazdani
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Current methods for few-shot fine-tuning of pretrained masked language models (PLMs) require carefully engineered prompts and verbalizers for each new task to convert examples into a cloze-format that the PLM can score. In this work, we propose Perfect, a simple and efficient method for few-shot fine-tuning of PLMs without relying on any such handcrafting, which is highly effective given as few as 32 data points. Perfect makes two key design choices: First, we show that manually engineered task prompts can be replaced with task-specific adapters that enable sample-efficient fine-tuning and reduce memory and storage costs by roughly factors of 5 and 100, respectively. Second, instead of using handcrafted verbalizers, we learn new multi-token label embeddings during fine-tuning, which are not tied to the model vocabulary and which allow us to avoid complex auto-regressive decoding. These embeddings are not only learnable from limited data but also enable nearly 100x faster training and inference. Experiments on a wide range of few shot NLP tasks demonstrate that Perfect, while being simple and efficient, also outperforms existing state-of-the-art few-shot learning methods. Our code is publicly available at


pdf bib
Multi-Task Retrieval for Knowledge-Intensive Tasks
Jean Maillard | Vladimir Karpukhin | Fabio Petroni | Wen-tau Yih | Barlas Oguz | Veselin Stoyanov | Gargi Ghosh
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Retrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditional methods like tf-idf and BM25, its performance degrades considerably when applied to out-of-domain data. Driven by the question of whether a neural retrieval model can be _universal_ and perform robustly on a wide variety of problems, we propose a multi-task trained model. Our approach not only outperforms previous methods in the few-shot setting, but also rivals specialised neural retrievers, even when in-domain training data is abundant. With the help of our retriever, we improve existing models for downstream tasks and closely match or improve the state of the art on multiple benchmarks.

pdf bib
Self-training Improves Pre-training for Natural Language Understanding
Jingfei Du | Edouard Grave | Beliz Gunel | Vishrav Chaudhary | Onur Celebi | Michael Auli | Veselin Stoyanov | Alexis Conneau
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a specific task, we introduce SentAugment, a data augmentation method which computes task-specific query embeddings from labeled data to retrieve sentences from a bank of billions of unlabeled sentences crawled from the web. Unlike previous semi-supervised methods, our approach does not require in-domain unlabeled data and is therefore more generally applicable. Experiments show that self-training is complementary to strong RoBERTa baselines on a variety of tasks. Our augmentation approach leads to scalable and effective self-training with improvements of up to 2.6% on standard text classification benchmarks. Finally, we also show strong gains on knowledge-distillation and few-shot learning.

pdf bib
Continual Few-Shot Learning for Text Classification
Ramakanth Pasunuru | Veselin Stoyanov | Mohit Bansal
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle numbers, perform coreference, etc. Our solutions to complex problems are still far from perfect, so it is important to create systems that can learn to correct mistakes quickly, incrementally, and with little training data. In this work, we propose a continual few-shot learning (CFL) task, in which a system is challenged with a difficult phenomenon and asked to learn to correct mistakes with only a few (10 to 15) training examples. To this end, we first create benchmarks based on previously annotated data: two NLI (ANLI and SNLI) and one sentiment analysis (IMDB) datasets. Next, we present various baselines from diverse paradigms (e.g., memory-aware synapses and Prototypical networks) and compare them on few-shot learning and continual few-shot learning setups. Our contributions are in creating a benchmark suite and evaluation protocol for continual few-shot learning on the text classification tasks, and making several interesting observations on the behavior of similarity-based methods. We hope that our work serves as a useful starting point for future work on this important topic.


pdf bib
Conversational Semantic Parsing
Armen Aghajanyan | Jean Maillard | Akshat Shrivastava | Keith Diedrick | Michael Haeger | Haoran Li | Yashar Mehdad | Veselin Stoyanov | Anuj Kumar | Mike Lewis | Sonal Gupta
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the representation, the session-based properties such as co-reference resolution and context carryover are processed downstream in a pipelined system. In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session. We release a new session-based, compositional task-oriented parsing dataset of 20k sessions consisting of 60k utterances. Unlike Dialog State Tracking Challenges, the queries in the dataset have compositional forms. We propose a new family of Seq2Seq models for the session-based parsing above, which also set state-of-the-art in ATIS, SNIPS, TOP and DSTC2. Notably, we improve the best known results on DSTC2 by up to 5 points for slot-carryover.

pdf bib
Emerging Cross-lingual Structure in Pretrained Language Models
Alexis Conneau | Shijie Wu | Haoran Li | Luke Zettlemoyer | Veselin Stoyanov
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so effective for cross-lingual transfer. We show, contrary to what was previously hypothesized, that transfer is possible even when there is no shared vocabulary across the monolingual corpora and also when the text comes from very different domains. The only requirement is that there are some shared parameters in the top layers of the multi-lingual encoder. To better understand this result, we also show that representations from monolingual BERT models in different languages can be aligned post-hoc quite effectively, strongly suggesting that, much like for non-contextual word embeddings, there are universal latent symmetries in the learned embedding spaces. For multilingual masked language modeling, these symmetries are automatically discovered and aligned during the joint training process.

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.

pdf bib
Unsupervised Cross-lingual Representation Learning at Scale
Alexis Conneau | Kartikay Khandelwal | Naman Goyal | Vishrav Chaudhary | Guillaume Wenzek | Francisco Guzmán | Edouard Grave | Myle Ott | Luke Zettlemoyer | Veselin Stoyanov
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages, using more than two terabytes of filtered CommonCrawl data. Our model, dubbed XLM-R, significantly outperforms multilingual BERT (mBERT) on a variety of cross-lingual benchmarks, including +14.6% average accuracy on XNLI, +13% average F1 score on MLQA, and +2.4% F1 score on NER. XLM-R performs particularly well on low-resource languages, improving 15.7% in XNLI accuracy for Swahili and 11.4% for Urdu over previous XLM models. We also present a detailed empirical analysis of the key factors that are required to achieve these gains, including the trade-offs between (1) positive transfer and capacity dilution and (2) the performance of high and low resource languages at scale. Finally, we show, for the first time, the possibility of multilingual modeling without sacrificing per-language performance; XLM-R is very competitive with strong monolingual models on the GLUE and XNLI benchmarks. We will make our code and models publicly available.

pdf bib
Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art
Patrick Lewis | Myle Ott | Jingfei Du | Veselin Stoyanov
Proceedings of the 3rd Clinical Natural Language Processing Workshop

A large array of pretrained models are available to the biomedical NLP (BioNLP) community. Finding the best model for a particular task can be difficult and time-consuming. For many applications in the biomedical and clinical domains, it is crucial that models can be built quickly and are highly accurate. We present a large-scale study across 18 established biomedical and clinical NLP tasks to determine which of several popular open-source biomedical and clinical NLP models work well in different settings. Furthermore, we apply recent advances in pretraining to train new biomedical language models, and carefully investigate the effect of various design choices on downstream performance. Our best models perform well in all of our benchmarks, and set new State-of-the-Art in 9 tasks. We release these models in the hope that they can help the community to speed up and increase the accuracy of BioNLP and text mining applications.

pdf bib
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference
Jingfei Du | Myle Ott | Haoran Li | Xing Zhou | Veselin Stoyanov
Findings of the Association for Computational Linguistics: EMNLP 2020

The state of the art on many NLP tasks is currently achieved by large pre-trained language models, which require a considerable amount of computation. We aim to reduce the inference cost in a setting where many different predictions are made on a single piece of text. In that case, computational cost during inference can be amortized over the different predictions (tasks) using a shared text encoder. We compare approaches for training such an encoder and show that encoders pre-trained over multiple tasks generalize well to unseen tasks. We also compare ways of extracting fixed- and limited-size representations from this encoder, including pooling features extracted from multiple layers or positions. Our best approach compares favorably to knowledge distillation, achieving higher accuracy and lower computational cost once the system is handling around 7 tasks. Further, we show that through binary quantization, we can reduce the size of the extracted representations by a factor of 16 to store them for later use. The resulting method offers a compelling solution for using large-scale pre-trained models at a fraction of the computational cost when multiple tasks are performed on the same text.


pdf bib
Knowledge-Augmented Language Model and Its Application to Unsupervised Named-Entity Recognition
Angli Liu | Jingfei Du | Veselin Stoyanov
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Traditional language models are unable to efficiently model entity names observed in text. All but the most popular named entities appear infrequently in text providing insufficient context. Recent efforts have recognized that context can be generalized between entity names that share the same type (e.g., person or location) and have equipped language models with an access to external knowledge base (KB). Our Knowledge-Augmented Language Model (KALM) continues this line of work by augmenting a traditional model with a KB. Unlike previous methods, however, we train with an end-to-end predictive objective optimizing the perplexity of text. We do not require any additional information such as named entity tags. In addition to improving language modeling performance, KALM learns to recognize named entities in an entirely unsupervised way by using entity type information latent in the model. On a Named Entity Recognition (NER) task, KALM achieves performance comparable with state-of-the-art supervised models. Our work demonstrates that named entities (and possibly other types of world knowledge) can be modeled successfully using predictive learning and training on large corpora of text without any additional information.


pdf bib
A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling
Ying Lin | Shengqi Yang | Veselin Stoyanov | Heng Ji
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer models using two layers of parameter sharing. On the first layer, we construct the basis of the architecture to provide universal word representation and feature extraction capability for all models. On the second level, we adopt different parameter sharing strategies for different transfer schemes. This architecture proves to be particularly effective for low-resource settings, when there are less than 200 training sentences for the target task. Using Name Tagging as a target task, our approach achieved 4.3%-50.5% absolute F-score gains compared to the mono-lingual single-task baseline model.

pdf bib
Simple Fusion: Return of the Language Model
Felix Stahlberg | James Cross | Veselin Stoyanov
Proceedings of the Third Conference on Machine Translation: Research Papers

Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and fixed language model (LM) with the scores of a translation model (TM) while the TM is trained from scratch. To achieve that, we train the translation model to predict the residual probability of the training data added to the prediction of the LM. This enables the TM to focus its capacity on modeling the source sentence since it can rely on the LM for fluency. We show that our method outperforms previous approaches to integrate LMs into NMT while the architecture is simpler as it does not require gating networks to balance TM and LM. We observe gains of between +0.24 and +2.36 BLEU on all four test sets (English-Turkish, Turkish-English, Estonian-English, Xhosa-English) on top of ensembles without LM. We compare our method with alternative ways to utilize monolingual data such as backtranslation, shallow fusion, and cold fusion.

pdf bib
XNLI: Evaluating Cross-lingual Sentence Representations
Alexis Conneau | Ruty Rinott | Guillaume Lample | Adina Williams | Samuel Bowman | Holger Schwenk | Veselin Stoyanov
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used beyond that language. Since collecting data in every language is not realistic, there has been a growing interest in cross-lingual language understanding (XLU) and low-resource cross-language transfer. In this work, we construct an evaluation set for XLU by extending the development and test sets of the Multi-Genre Natural Language Inference Corpus (MultiNLI) to 14 languages, including low-resource languages such as Swahili and Urdu. We hope that our dataset, dubbed XNLI, will catalyze research in cross-lingual sentence understanding by providing an informative standard evaluation task. In addition, we provide several baselines for multilingual sentence understanding, including two based on machine translation systems, and two that use parallel data to train aligned multilingual bag-of-words and LSTM encoders. We find that XNLI represents a practical and challenging evaluation suite, and that directly translating the test data yields the best performance among available baselines.


pdf bib
SemEval-2016 Task 4: Sentiment Analysis in Twitter
Preslav Nakov | Alan Ritter | Sara Rosenthal | Fabrizio Sebastiani | Veselin Stoyanov
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)


pdf bib
SemEval-2015 Task 10: Sentiment Analysis in Twitter
Sara Rosenthal | Preslav Nakov | Svetlana Kiritchenko | Saif Mohammad | Alan Ritter | Veselin Stoyanov
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)


pdf bib
SemEval-2014 Task 9: Sentiment Analysis in Twitter
Sara Rosenthal | Alan Ritter | Preslav Nakov | Veselin Stoyanov
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)


pdf bib
SemEval-2013 Task 2: Sentiment Analysis in Twitter
Preslav Nakov | Sara Rosenthal | Zornitsa Kozareva | Veselin Stoyanov | Alan Ritter | Theresa Wilson
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)


pdf bib
Easy-first Coreference Resolution
Veselin Stoyanov | Jason Eisner
Proceedings of COLING 2012

pdf bib
A Context-Aware Approach to Entity Linking
Veselin Stoyanov | James Mayfield | Tan Xu | Douglas Oard | Dawn Lawrie | Tim Oates | Tim Finin
Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX)

pdf bib
Minimum-Risk Training of Approximate CRF-Based NLP Systems
Veselin Stoyanov | Jason Eisner
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


pdf bib
Reconciling OntoNotes: Unrestricted Coreference Resolution in OntoNotes with Reconcile.
Veselin Stoyanov | Uday Babbar | Pracheer Gupta | Claire Cardie
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task

pdf bib
Automatically Creating General-Purpose Opinion Summaries from Text
Veselin Stoyanov | Claire Cardie
Proceedings of the International Conference Recent Advances in Natural Language Processing 2011


pdf bib
Coreference Resolution with Reconcile
Veselin Stoyanov | Claire Cardie | Nathan Gilbert | Ellen Riloff | David Buttler | David Hysom
Proceedings of the ACL 2010 Conference Short Papers


pdf bib
Conundrums in Noun Phrase Coreference Resolution: Making Sense of the State-of-the-Art
Veselin Stoyanov | Nathan Gilbert | Claire Cardie | Ellen Riloff
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP


pdf bib
Annotating Topics of Opinions
Veselin Stoyanov | Claire Cardie
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Fine-grained subjectivity analysis has been the subject of much recent research attention. As a result, the field has gained a number of working definitions, technical approaches and manually annotated corpora that cover many facets of subjectivity. Little work has been done, however, on one aspect of fine-grained opinions - the specification and identification of opinion topics. In particular, due to the difficulty of manual opinion topic annotation, no general-purpose opinion corpus with information about topics of fine-grained opinions currently exists. In this paper, we propose a methodology for the manual annotation of opinion topics and use it to annotate a portion of an existing general-purpose opinion corpus with opinion topic information. Inter-annotator agreement results according to a number of metrics suggest that the annotations are reliable.

pdf bib
Topic Identification for Fine-Grained Opinion Analysis
Veselin Stoyanov | Claire Cardie
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)


pdf bib
Toward Opinion Summarization: Linking the Sources
Veselin Stoyanov | Claire Cardie
Proceedings of the Workshop on Sentiment and Subjectivity in Text

pdf bib
Partially Supervised Coreference Resolution for Opinion Summarization through Structured Rule Learning
Veselin Stoyanov | Claire Cardie
Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing


pdf bib
Multi-Perspective Question Answering Using the OpQA Corpus
Veselin Stoyanov | Claire Cardie | Janyce Wiebe
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing