Mike Lewis


2020

pdf bib
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
Alex Wang | Kyunghyun Cho | Mike Lewis
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

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.

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
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
Grounded Adaptation for Zero-shot Executable Semantic Parsing
Victor Zhong | Mike Lewis | Sida I. Wang | Luke Zettlemoyer
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We propose Grounded Adaptation for Zeroshot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified through execution. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.

2019

pdf bib
Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog
Panupong Pasupat | Sonal Gupta | Karishma Mandyam | Rushin Shah | Mike Lewis | 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)

We propose a semantic parser for parsing compositional utterances into Task Oriented Parse (TOP), a tree representation that has intents and slots as labels of nesting tree nodes. Our parser is span-based: it scores labels of the tree nodes covering each token span independently, but then decodes a valid tree globally. In contrast to previous sequence decoding approaches and other span-based parsers, we (1) improve the training speed by removing the need to run the decoder at training time; and (2) introduce edge scores, which model relations between parent and child labels, to mitigate the independence assumption between node labels and improve accuracy. Our best parser outperforms previous methods on the TOP dataset of mixed-domain task-oriented utterances in both accuracy and training speed.

pdf bib
Strategies for Structuring Story Generation
Angela Fan | Mike Lewis | Yann Dauphin
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Writers often rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and introduce new models which decompose stories by abstracting over actions and entities. The model first generates the predicate-argument structure of the text, where different mentions of the same entity are marked with placeholder tokens. It then generates a surface realization of the predicate-argument structure, and finally replaces the entity placeholders with context-sensitive names and references. Human judges prefer the stories from our models to a wide range of previous approaches to hierarchical text generation. Extensive analysis shows that our methods can help improve the diversity and coherence of events and entities in generated stories.

pdf bib
Proceedings of the First Workshop on NLP for Conversational AI
Yun-Nung Chen | Tania Bedrax-Weiss | Dilek Hakkani-Tur | Anuj Kumar | Mike Lewis | Thang-Minh Luong | Pei-Hao Su | Tsung-Hsien Wen
Proceedings of the First Workshop on NLP for Conversational AI

pdf bib
Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog
Sebastian Schuster | Sonal Gupta | Rushin Shah | Mike Lewis
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)

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data collection for machine learning models for this task is time-consuming, it is desirable to make use of existing data in a high-resource language to train models in low-resource languages. However, development of such models has largely been hindered by the lack of multilingual training data. In this paper, we present a new data set of 57k annotated utterances in English (43k), Spanish (8.6k) and Thai (5k) across the domains weather, alarm, and reminder. We use this data set to evaluate three different cross-lingual transfer methods: (1) translating the training data, (2) using cross-lingual pre-trained embeddings, and (3) a novel method of using a multilingual machine translation encoder as contextual word representations. We find that given several hundred training examples in the the target language, the latter two methods outperform translating the training data. Further, in very low-resource settings, multilingual contextual word representations give better results than using cross-lingual static embeddings. We also compare the cross-lingual methods to using monolingual resources in the form of contextual ELMo representations and find that given just small amounts of target language data, this method outperforms all cross-lingual methods, which highlights the need for more sophisticated cross-lingual methods.

2018

pdf bib
A Dataset for Telling the Stories of Social Media Videos
Spandana Gella | Mike Lewis | Marcus Rohrbach
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Video content on social media platforms constitutes a major part of the communication between people, as it allows everyone to share their stories. However, if someone is unable to consume video, either due to a disability or network bandwidth, this severely limits their participation and communication. Automatically telling the stories using multi-sentence descriptions of videos would allow bridging this gap. To learn and evaluate such models, we introduce VideoStory a new large-scale dataset for video description as a new challenge for multi-sentence video description. Our VideoStory captions dataset is complementary to prior work and contains 20k videos posted publicly on a social media platform amounting to 396 hours of video with 123k sentences, temporally aligned to the video.

pdf bib
Neural Compositional Denotational Semantics for Question Answering
Nitish Gupta | Mike Lewis
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Answering compositional questions requiring multi-step reasoning is challenging. We introduce an end-to-end differentiable model for interpreting questions about a knowledge graph (KG), which is inspired by formal approaches to semantics. Each span of text is represented by a denotation in a KG and a vector that captures ungrounded aspects of meaning. Learned composition modules recursively combine constituent spans, culminating in a grounding for the complete sentence which answers the question. For example, to interpret “not green”, the model represents “green” as a set of KG entities and “not” as a trainable ungrounded vector—and then uses this vector to parameterize a composition function that performs a complement operation. For each sentence, we build a parse chart subsuming all possible parses, allowing the model to jointly learn both the composition operators and output structure by gradient descent from end-task supervision. The model learns a variety of challenging semantic operators, such as quantifiers, disjunctions and composed relations, and infers latent syntactic structure. It also generalizes well to longer questions than seen in its training data, in contrast to RNN, its tree-based variants, and semantic parsing baselines.

pdf bib
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
Sonal Gupta | Rushin Shah | Mrinal Mohit | Anuj Kumar | Mike Lewis
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots. Previous work on task oriented intent and slot-filling work has been restricted to one intent per query and one slot label per token, and thus cannot model complex compositional requests. Alternative semantic parsing systems have represented queries as logical forms, but these are challenging to annotate and parse. We propose a hierarchical annotation scheme for semantic parsing that allows the representation of compositional queries, and can be efficiently and accurately parsed by standard constituency parsing models. We release a dataset of 44k annotated queries (http://fb.me/semanticparsingdialog), and show that parsing models outperform sequence-to-sequence approaches on this dataset.

pdf bib
Hierarchical Neural Story Generation
Angela Fan | Mike Lewis | Yann Dauphin
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text. We gain further improvements with a novel form of model fusion that improves the relevance of the story to the prompt, and adding a new gated multi-scale self-attention mechanism to model long-range context. Experiments show large improvements over strong baselines on both automated and human evaluations. Human judges prefer stories generated by our approach to those from a strong non-hierarchical model by a factor of two to one.

2017

pdf bib
Deep Semantic Role Labeling: What Works and What’s Next
Luheng He | Kenton Lee | Mike Lewis | Luke Zettlemoyer
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use a deep highway BiLSTM architecture with constrained decoding, while observing a number of recent best practices for initialization and regularization. Our 8-layer ensemble model achieves 83.2 F1 on theCoNLL 2005 test set and 83.4 F1 on CoNLL 2012, roughly a 10% relative error reduction over the previous state of the art. Extensive empirical analysis of these gains show that (1) deep models excel at recovering long-distance dependencies but can still make surprisingly obvious errors, and (2) that there is still room for syntactic parsers to improve these results.

pdf bib
A Corpus of Natural Language for Visual Reasoning
Alane Suhr | Mike Lewis | James Yeh | Yoav Artzi
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We present a new visual reasoning language dataset, containing 92,244 pairs of examples of natural statements grounded in synthetic images with 3,962 unique sentences. We describe a method of crowdsourcing linguistically-diverse data, and present an analysis of our data. The data demonstrates a broad set of linguistic phenomena, requiring visual and set-theoretic reasoning. We experiment with various models, and show the data presents a strong challenge for future research.

pdf bib
End-to-end Neural Coreference Resolution
Kenton Lee | Luheng He | Mike Lewis | Luke Zettlemoyer
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span embeddings that combine context-dependent boundary representations with a head-finding attention mechanism. It is trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions. Experiments demonstrate state-of-the-art performance, with a gain of 1.5 F1 on the OntoNotes benchmark and by 3.1 F1 using a 5-model ensemble, despite the fact that this is the first approach to be successfully trained with no external resources.

pdf bib
Deal or No Deal? End-to-End Learning of Negotiation Dialogues
Mike Lewis | Denis Yarats | Yann Dauphin | Devi Parikh | Dhruv Batra
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. Negotiations require complex communication and reasoning skills, but success is easy to measure, making this an interesting task for AI. We gather a large dataset of human-human negotiations on a multi-issue bargaining task, where agents who cannot observe each other’s reward functions must reach an agreement (or a deal) via natural language dialogue. For the first time, we show it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states. We also introduce dialogue rollouts, in which the model plans ahead by simulating possible complete continuations of the conversation, and find that this technique dramatically improves performance. Our code and dataset are publicly available.

2016

pdf bib
Human-in-the-Loop Parsing
Luheng He | Julian Michael | Mike Lewis | Luke Zettlemoyer
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Global Neural CCG Parsing with Optimality Guarantees
Kenton Lee | Mike Lewis | Luke Zettlemoyer
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
LSTM CCG Parsing
Mike Lewis | Kenton Lee | Luke Zettlemoyer
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2015

pdf bib
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
Luheng He | Mike Lewis | Luke Zettlemoyer
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Joint A* CCG Parsing and Semantic Role Labelling
Mike Lewis | Luheng He | Luke Zettlemoyer
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Combining Formal and Distributional Models of Temporal and Intensional Semantics
Mike Lewis | Mark Steedman
Proceedings of the ACL 2014 Workshop on Semantic Parsing

pdf bib
Improved CCG Parsing with Semi-supervised Supertagging
Mike Lewis | Mark Steedman
Transactions of the Association for Computational Linguistics, Volume 2

Current supervised parsers are limited by the size of their labelled training data, making improving them with unlabelled data an important goal. We show how a state-of-the-art CCG parser can be enhanced, by predicting lexical categories using unsupervised vector-space embeddings of words. The use of word embeddings enables our model to better generalize from the labelled data, and allows us to accurately assign lexical categories without depending on a POS-tagger. Our approach leads to substantial improvements in dependency parsing results over the standard supervised CCG parser when evaluated on Wall Street Journal (0.8%), Wikipedia (1.8%) and biomedical (3.4%) text. We compare the performance of two recently proposed approaches for classification using a wide variety of word embeddings. We also give a detailed error analysis demonstrating where using embeddings outperforms traditional feature sets, and showing how including POS features can decrease accuracy.

pdf bib
A* CCG Parsing with a Supertag-factored Model
Mike Lewis | Mark Steedman
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Unsupervised Induction of Cross-Lingual Semantic Relations
Mike Lewis | Mark Steedman
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Combined Distributional and Logical Semantics
Mike Lewis | Mark Steedman
Transactions of the Association for Computational Linguistics, Volume 1

We introduce a new approach to semantics which combines the benefits of distributional and formal logical semantics. Distributional models have been successful in modelling the meanings of content words, but logical semantics is necessary to adequately represent many function words. We follow formal semantics in mapping language to logical representations, but differ in that the relational constants used are induced by offline distributional clustering at the level of predicate-argument structure. Our clustering algorithm is highly scalable, allowing us to run on corpora the size of Gigaword. Different senses of a word are disambiguated based on their induced types. We outperform a variety of existing approaches on a wide-coverage question answering task, and demonstrate the ability to make complex multi-sentence inferences involving quantifiers on the FraCaS suite.