Papers

Learn more about AI2's Lasting Impact Award
Viewing 211-220 of 224 papers
  • Simple and Effective Multi-Paragraph Reading Comprehension

    Christopher Clark, Matt GardnerACL2018 We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well calibrated confidence scores for their results on individual…
  • Ultra-Fine Entity Typing

    Eunsol Choi, Omer Levy, Yejin Choi and Luke ZettlemoyerACL2018 We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate types for the target entity. This formulation allows us to…
  • A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

    Dongyeop Kang, Waleed Ammar, Bhavana Dalvi Mishra, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, Roy SchwartzNAACL-HLT2018 Peer reviewing is a central component in the scientific publishing process. We present the first public dataset of scientific peer reviews available for research pur- poses (PeerRead v1), providing an opportunity to study this important artifact. The dataset…
  • Annotation Artifacts in Natural Language Inference Data

    Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Sam Bowman and Noah A. SmithNAACL2018 Large-scale datasets for natural language inference are created by presenting crowd workers with a sentence (premise), and asking them to generate three new sentences (hypotheses) that it entails, contradicts, or is logically neutral with respect to. We show…
  • Deep Contextualized Word Representations

    Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke ZettlemoyerNAACL2018 We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are…
  • SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines

    Roy Schwartz, Sam Thomson and Noah A. SmithACL2018 Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two approaches. SoPa combines…
  • Dynamic Entity Representations in Neural Language Models

    Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, Noah A. SmithEMNLP2017 Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically update their representations, and contextually generate their…
  • Learning a Neural Semantic Parser from User Feedback

    Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, and Luke ZettlemoyerACL2017 We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural sequence models to…
  • Semi-supervised sequence tagging with bidirectional language models

    Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, and Russell PowerACL2017 Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce context sensitive…
  • Deep Semantic Role Labeling: What Works and What's Next

    Luheng He, Kenton Lee, Mike Lewis, Luke S. ZettlemoyerACL2017 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…