Doug Downey


Embedding Recycling for Language Models
Jon Saad-falcon | Amanpreet Singh | Luca Soldaini | Mike D’arcy | Arman Cohan | Doug Downey
Findings of the Association for Computational Linguistics: EACL 2023

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings produced in previous runs to speed training and inference of future ones. We refer to this approach as embedding recycling (ER). While multiple ER techniques have been proposed, their practical effectiveness is still unknown because existing evaluations consider very few models and do not adequately account for overhead costs. We perform an extensive evaluation of ER across eight different models (17 to 900 million parameters) and fourteen tasks in English. We show how a simple ER technique that caches activations from an intermediate layer of a pretrained model, and learns task-specific adapters on the later layers, is broadly effective. For the best-performing baseline in our experiments (DeBERTa-v2 XL), adding a precomputed cache results in a 90% speedup during training and 87-91% speedup for inference, with negligible impact on accuracy. Our analysis reveals important areas of future work.

Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions
Emily Allaway | Jena D. Hwang | Chandra Bhagavatula | Kathleen Mckeown | Doug Downey | Yejin Choi
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Generics express generalizations about the world (e.g., birds can fly) that are not universally true (e.g., newborn birds and penguins cannot fly). Commonsense knowledge bases, used extensively in NLP, encode some generic knowledge but rarely enumerate such exceptions and knowing when a generic statement holds or does not hold true is crucial for developing a comprehensive understanding of generics. We present a novel framework informed by linguistic theory to generate exemplars—specific cases when a generic holds true or false. We generate ~19k exemplars for ~650 generics and show that our framework outperforms a strong GPT-3 baseline by 12.8 precision points. Our analysis highlights the importance of linguistic theory-based controllability for generating exemplars, the insufficiency of knowledge bases as a source of exemplars, and the challenges exemplars pose for the task of natural language inference.


ABNIRML: Analyzing the Behavior of Neural IR Models
Sean MacAvaney | Sergey Feldman | Nazli Goharian | Doug Downey | Arman Cohan
Transactions of the Association for Computational Linguistics, Volume 10

Pretrained contextualized language models such as BERT and T5 have established a new state-of-the-art for ad-hoc search. However, it is not yet well understood why these methods are so effective, what makes some variants more effective than others, and what pitfalls they may have. We present a new comprehensive framework for Analyzing the Behavior of Neural IR ModeLs (ABNIRML), which includes new types of diagnostic probes that allow us to test several characteristics—such as writing styles, factuality, sensitivity to paraphrasing and word order—that are not addressed by previous techniques. To demonstrate the value of the framework, we conduct an extensive empirical study that yields insights into the factors that contribute to the neural model’s gains, and identify potential unintended biases the models exhibit. Some of our results confirm conventional wisdom, for example, that recent neural ranking models rely less on exact term overlap with the query, and instead leverage richer linguistic information, evidenced by their higher sensitivity to word and sentence order. Other results are more surprising, such as that some models (e.g., T5 and ColBERT) are biased towards factually correct (rather than simply relevant) texts. Further, some characteristics vary even for the same base language model, and other characteristics can appear due to random variations during model training.1

VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
Zejiang Shen | Kyle Lo | Lucy Lu Wang | Bailey Kuehl | Daniel S. Weld | Doug Downey
Transactions of the Association for Computational Linguistics, Volume 10

Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, for example, each token’s 2D position on the page, into language model pretraining. We introduce new methods that explicitly model VIsual LAyout (VILA) groups, that is, text lines or text blocks, to further improve performance. In our I-VILA approach, we show that simply inserting special tokens denoting layout group boundaries into model inputs can lead to a 1.9% Macro F1 improvement in token classification. In the H-VILA approach, we show that hierarchical encoding of layout-groups can result in up to 47% inference time reduction with less than 0.8% Macro F1 loss. Unlike prior layout-aware approaches, our methods do not require expensive additional pretraining, only fine-tuning, which we show can reduce training cost by up to 95%. Experiments are conducted on a newly curated evaluation suite, S2-VLUE, that unifies existing automatically labeled datasets and includes a new dataset of manual annotations covering diverse papers from 19 scientific disciplines. Pre-trained weights, benchmark datasets, and source code are available at

Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search
Daniel King | Zejiang Shen | Nishant Subramani | Daniel S. Weld | Iz Beltagy | Doug Downey
Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)

Abstractive summarization systems today produce fluent and relevant output, but often “hallucinate” statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. Based on our findings, we present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations. Given the model states and outputs at a given step, PINOCCHIO detects likely model hallucinations based on various measures of attribution to the source text. PINOCCHIO backtracks to find more consistent output, and can opt to produce no summary at all when no consistent generation can be found. In experiments, we find that PINOCCHIO improves the consistency of generation by an average of 67% on two abstractive summarization datasets, without hurting recall.

Few-Shot Self-Rationalization with Natural Language Prompts
Ana Marasovic | Iz Beltagy | Doug Downey | Matthew Peters
Findings of the Association for Computational Linguistics: NAACL 2022

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a large amount of human-written free-text explanations for each task which hinders their broader usage. We propose to study a more realistic setting of self-rationalization using few training examples. We present FEB—a standardized collection of four existing English-language datasets and associated metrics. We identify the right prompting approach by extensively exploring natural language prompts on FEB. Then, by using this prompt and scaling the model size, we demonstrate that making progress on few-shot self-rationalization is possible. We show there is still ample room for improvement in this task: the average plausibility of generated explanations assessed by human annotators is at most 51% (with GPT-3), while plausibility of human explanations is 76%. We hope that FEB and our proposed approach will spur the community to take on the few-shot self-rationalization challenge.

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models
Victor Bursztyn | David Demeter | Doug Downey | Larry Birnbaum
Findings of the Association for Computational Linguistics: EMNLP 2022

How to usefully encode compositional task structure has long been a core challenge in AI. Recent work in chain of thought prompting has shown that for very large neural language models (LMs), explicitly demonstrating the inferential steps involved in a target task may improve performance over end-to-end learning that focuses on the target task alone. However, chain of thought prompting has significant limitations due to its dependency on huge pretrained LMs. In this work, we present compositional fine-tuning (CFT): an approach based on explicitly decomposing a target task into component tasks, and then fine-tuning smaller LMs on a curriculum of such component tasks. We apply CFT to recommendation tasks in two domains, world travel and local dining, as well as a previously studied inferential task (sports understanding). We show that CFT outperforms end-to-end learning even with equal amounts of data, and gets consistently better as more component tasks are modeled via fine-tuning. Compared with chain of thought prompting, CFT performs at least as well using LMs only 7.4% of the size, and is moreover applicable to task domains for which data are not available during pretraining.

ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts
Sonia Murthy | Kyle Lo | Daniel King | Chandra Bhagavatula | Bailey Kuehl | Sophie Johnson | Jonathan Borchardt | Daniel Weld | Tom Hope | Doug Downey
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Systems that automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per concept, which fails to account for the many ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions oftarget concepts in terms of different reference concepts. In a user study, we find that users prefer (1) descriptions produced by our end-to-end system, and (2) multiple descriptions to a single “best” description. We release the ACCoRD corpus which includes 1,275 labeled contexts and 1,787 expert-authored concept descriptions to support research on our task.


Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains
David Demeter | Doug Downey
Proceedings of the 25th Conference on Computational Natural Language Learning

The capabilities of today’s natural language processing systems are typically evaluated using large datasets of curated questions and answers. While these are critical benchmarks of progress, they also suffer from weakness due to artificial distributions and incomplete knowledge. Artifacts arising from artificial distributions can overstate language model performance, while incomplete knowledge limits fine-grained analysis. In this work, we introduce a complementary benchmarking approach based on SimPlified Language Activity Traces (SPLAT). SPLATs are corpora of language encodings of activity in some closed domain (we study traces from chess and baseball games in this work). SPLAT datasets use naturally-arising distributions, allow the generation of question-answer pairs at scale, and afford complete knowledge in their closed domains. We show that language models of three different architectures can answer questions about world states using only verb-like encodings of activity. Our approach is extensible to new language models and additional question-answering tasks.

“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems
Victor Bursztyn | Jennifer Healey | Nedim Lipka | Eunyee Koh | Doug Downey | Larry Birnbaum
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Conversations aimed at determining good recommendations are iterative in nature. People often express their preferences in terms of a critique of the current recommendation (e.g., “It doesn’t look good for a date”), requiring some degree of common sense for a preference to be inferred. In this work, we present a method for transforming a user critique into a positive preference (e.g., “I prefer more romantic”) in order to retrieve reviews pertaining to potentially better recommendations (e.g., “Perfect for a romantic dinner”). We leverage a large neural language model (LM) in a few-shot setting to perform critique-to-preference transformation, and we test two methods for retrieving recommendations: one that matches embeddings, and another that fine-tunes an LM for the task. We instantiate this approach in the restaurant domain and evaluate it using a new dataset of restaurant critiques. In an ablation study, we show that utilizing critique-to-preference transformation improves recommendations, and that there are at least three general cases that explain this improved performance.


Stolen Probability: A Structural Weakness of Neural Language Models
David Demeter | Gregory Kimmel | Doug Downey
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Neural Network Language Models (NNLMs) generate probability distributions by applying a softmax function to a distance metric formed by taking the dot product of a prediction vector with all word vectors in a high-dimensional embedding space. The dot-product distance metric forms part of the inductive bias of NNLMs. Although NNLMs optimize well with this inductive bias, we show that this results in a sub-optimal ordering of the embedding space that structurally impoverishes some words at the expense of others when assigning probability. We present numerical, theoretical and empirical analyses which show that words on the interior of the convex hull in the embedding space have their probability bounded by the probabilities of the words on the hull.

SPECTER: Document-level Representation Learning using Citation-informed Transformers
Arman Cohan | Sergey Feldman | Iz Beltagy | Doug Downey | Daniel Weld
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, accurate embeddings of documents are a necessity. We propose SPECTER, a new method to generate document-level embedding of scientific papers based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, Specter can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that Specter outperforms a variety of competitive baselines on the benchmark.

Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Suchin Gururangan | Ana Marasović | Swabha Swayamdipta | Kyle Lo | Iz Beltagy | Doug Downey | Noah A. Smith
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Language models pretrained on text from a wide variety of sources form the foundation of today’s NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the domain of a target task. We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks, showing that a second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains, under both high- and low-resource settings. Moreover, adapting to the task’s unlabeled data (task-adaptive pretraining) improves performance even after domain-adaptive pretraining. Finally, we show that adapting to a task corpus augmented using simple data selection strategies is an effective alternative, especially when resources for domain-adaptive pretraining might be unavailable. Overall, we consistently find that multi-phase adaptive pretraining offers large gains in task performance.

Generative Data Augmentation for Commonsense Reasoning
Yiben Yang | Chaitanya Malaviya | Jared Fernandez | Swabha Swayamdipta | Ronan Le Bras | Ji-Ping Wang | Chandra Bhagavatula | Yejin Choi | Doug Downey
Findings of the Association for Computational Linguistics: EMNLP 2020

Recent advances in commonsense reasoning depend on large-scale human-annotated training sets to achieve peak performance. However, manual curation of training sets is expensive and has been shown to introduce annotation artifacts that neural models can readily exploit and overfit to. We propose a novel generative data augmentation technique, G-DAUGˆC, that aims to achieve more accurate and robust learning in a low-resource setting. Our approach generates synthetic examples using pretrained language models and selects the most informative and diverse set of examples for data augmentation. On experiments with multiple commonsense reasoning benchmarks, G-DAUGˆC consistently outperforms existing data augmentation methods based on back-translation, establishing a new state-of-the-art on WinoGrande, CODAH, and CommonsenseQA, as well as enhances out-of-distribution generalization, proving to be robust against adversaries or perturbations. Our analysis demonstrates that G-DAUGˆC produces a diverse set of fluent training examples, and that its selection and training approaches are important for performance.


CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense
Michael Chen | Mike D’Arcy | Alisa Liu | Jared Fernandez | Doug Downey
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP

Commonsense reasoning is a critical AI capability, but it is difficult to construct challenging datasets that test common sense. Recent neural question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks. These systems do not possess human-level common sense, but are able to exploit limitations of the datasets to achieve human-level scores. We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing common sense. CODAH forms a challenging extension to the recently-proposed SWAG dataset, which tests commonsense knowledge using sentence-completion questions that describe situations observed in video. To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems. Workers are rewarded for submissions that models fail to answer correctly both before and after fine-tuning (in cross-validation). We create 2.8k questions via this procedure and evaluate the performance of multiple state-of-the-art question answering systems on our dataset. We observe a significant gap between human performance, which is 95.3%, and the performance of the best baseline accuracy of 65.3% by the OpenAI GPT model.

Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models
Yiben Yang | Ji-Ping Wang | Doug Downey
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)

Recurrent neural network language models (RNNLM) form a valuable foundation for many NLP systems, but training the models can be computationally expensive, and may take days to train on a large corpus. We explore a technique that uses large corpus n-gram statistics as a regularizer for training a neural network LM on a smaller corpus. In experiments with the Billion-Word and Wikitext corpora, we show that the technique is effective, and more time-efficient than simply training on a larger sequential corpus. We also introduce new strategies for selecting the most informative n-grams, and show that these boost efficiency.

A Semantic Cover Approach for Topic Modeling
Rajagopal Venkatesaramani | Doug Downey | Bradley Malin | Yevgeniy Vorobeychik
Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)

We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with a set of topic words based on semantic similarity, defined in terms of a word embedding. Computing a topic cover amounts to solving a minimum set cover problem. Our evaluation compares our topic modeling approach to Latent Dirichlet Allocation (LDA) on three metrics: 1) qualitative topic match, measured using evaluations by Amazon Mechanical Turk (MTurk) workers, 2) performance on classification tasks using each topic model as a sparse feature representation, and 3) topic coherence. We find that qualitative judgments significantly favor our approach, the method outperforms LDA on topic coherence, and is comparable to LDA on document classification tasks.


Construction of the Literature Graph in Semantic Scholar
Waleed Ammar | Dirk Groeneveld | Chandra Bhagavatula | Iz Beltagy | Miles Crawford | Doug Downey | Jason Dunkelberger | Ahmed Elgohary | Sergey Feldman | Vu Ha | Rodney Kinney | Sebastian Kohlmeier | Kyle Lo | Tyler Murray | Hsu-Han Ooi | Matthew Peters | Joanna Power | Sam Skjonsberg | Lucy Lu Wang | Chris Wilhelm | Zheng Yuan | Madeleine van Zuylen | Oren Etzioni
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)

We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph consists of more than 280M nodes, representing papers, authors, entities and various interactions between them (e.g., authorships, citations, entity mentions). We reduce literature graph construction into familiar NLP tasks (e.g., entity extraction and linking), point out research challenges due to differences from standard formulations of these tasks, and report empirical results for each task. The methods described in this paper are used to enable semantic features in

Extracting Commonsense Properties from Embeddings with Limited Human Guidance
Yiben Yang | Larry Birnbaum | Ji-Ping Wang | Doug Downey
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

pdf bib
Sampling Informative Training Data for RNN Language Models
Jared Fernandez | Doug Downey
Proceedings of ACL 2018, Student Research Workshop

We propose an unsupervised importance sampling approach to selecting training data for recurrent neural network (RNNs) language models. To increase the information content of the training set, our approach preferentially samples high perplexity sentences, as determined by an easily queryable n-gram language model. We experimentally evaluate the heldout perplexity of models trained with our various importance sampling distributions. We show that language models trained on data sampled using our proposed approach outperform models trained over randomly sampled subsets of both the Billion Word (Chelba et al., 2014 Wikitext-103 benchmark corpora (Merity et al., 2016).

Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models
Thanapon Noraset | Doug Downey | Lidong Bing
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recurrent neural network language models (RNNLMs) are the current standard-bearer for statistical language modeling. However, RNNLMs only estimate probabilities for complete sequences of text, whereas some applications require context-independent phrase probabilities instead. In this paper, we study how to compute an RNNLM’s em marginal probability: the probability that the model assigns to a short sequence of text when the preceding context is not known. We introduce a simple method of altering the RNNLM training to make the model more accurate at marginal estimation. Our experiments demonstrate that the technique is effective compared to baselines including the traditional RNNLM probability and an importance sampling approach. Finally, we show how we can use the marginal estimation to improve an RNNLM by training the marginals to match n-gram probabilities from a larger corpus.


VecShare: A Framework for Sharing Word Representation Vectors
Jared Fernandez | Zhaocheng Yu | Doug Downey
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Many Natural Language Processing (NLP) models rely on distributed vector representations of words. Because the process of training word vectors can require large amounts of data and computation, NLP researchers and practitioners often utilize pre-trained embeddings downloaded from the Web. However, finding the best embeddings for a given task is difficult, and can be computationally prohibitive. We present a framework, called VecShare, that makes it easy to share and retrieve word embeddings on the Web. The framework leverages a public data-sharing infrastructure to host embedding sets, and provides automated mechanisms for retrieving the embeddings most similar to a given corpus. We perform an experimental evaluation of VecShare’s similarity strategies, and show that they are effective at efficiently retrieving embeddings that boost accuracy in a document classification task. Finally, we provide an open-source Python library for using the VecShare framework.


Efficient Methods for Incorporating Knowledge into Topic Models
Yi Yang | Doug Downey | Jordan Boyd-Graber
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

Efficient Methods for Inferring Large Sparse Topic Hierarchies
Doug Downey | Chandra Bhagavatula | Yi Yang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)


Adding High-Precision Links to Wikipedia
Thanapon Noraset | Chandra Bhagavatula | Doug Downey
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Active Learning with Constrained Topic Model
Yi Yang | Shimei Pan | Doug Downey | Kunpeng Zhang
Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces

Learning Representations for Weakly Supervised Natural Language Processing Tasks
Fei Huang | Arun Ahuja | Doug Downey | Yi Yang | Yuhong Guo | Alexander Yates
Computational Linguistics, Volume 40, Issue 1 - March 2014


Scaling Semi-supervised Naive Bayes with Feature Marginals
Michael Lucas | Doug Downey
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Overcoming the Memory Bottleneck in Distributed Training of Latent Variable Models of Text
Yi Yang | Alexander Yates | Doug Downey
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


Language Models as Representations for Weakly Supervised NLP Tasks
Fei Huang | Alexander Yates | Arun Ahuja | Doug Downey
Proceedings of the Fifteenth Conference on Computational Natural Language Learning

Local and Global Algorithms for Disambiguation to Wikipedia
Lev Ratinov | Dan Roth | Doug Downey | Mike Anderson
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies


Improved Extraction Assessment through Better Language Models
Arun Ahuja | Doug Downey
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics


pdf bib
It’s a Contradiction – no, it’s not: A Case Study using Functional Relations
Alan Ritter | Stephen Soderland | Doug Downey | Oren Etzioni
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing


Sparse Information Extraction: Unsupervised Language Models to the Rescue
Doug Downey | Stefan Schoenmackers | Oren Etzioni
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics


KnowItNow: Fast, Scalable Information Extraction from the Web
Michael J. Cafarella | Doug Downey | Stephen Soderland | Oren Etzioni
Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing