Learn more about AI2's Lasting Impact Award
All Projects
All Years
Viewing 441-450 of 553 papers
  • Automatic Selection of Context Configurations for Improved Class-Specific Word Representations

    Ivan Vulic, Roy Schwartz, Ari Rappoport, Roi Reichart, and Anna KorhonenCoNLL2017 This paper is concerned with identifying contexts useful for training word representation models for different word classes such as adjectives (A), verbs (V), and nouns (N). We introduce a simple yet effective framework for an automatic selection of class… more
  • Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers

    Mark Hopkins, Cristian Petrescu-Prahova, Roie Levin, Ronan Le Bras, Alvaro Herrasti, and Vidur JoshiEMNLP2017 We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions--the math portion of the Scholastic Aptitude Test (SAT). By using a tree… more
  • Bidirectional Attention Flow for Machine Comprehension

    Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh HajishirziICLR2017 Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use… more
  • Commonly Uncommon: Semantic Sparsity in Situation Recognition

    Mark Yatskar, Vicente Ordonez, Luke Zettlemoyer, and Ali FarhadiCVPR2017 Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic sparsity in… more
  • Crowdsourcing Multiple Choice Science Questions

    Johannes Welbl, Nelson F. Liu, and Matt GardnerEMNLP • Workshop on Noisy User-generated Text2017 We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality, relevance or diversity in the answer options. Our method… more
  • 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… more
  • Distilling Task Knowledge from How-To Communities

    Cuong Xuan Chu, Niket Tandon, and Gerhard WeikumWWW2017 Knowledge graphs have become a fundamental asset for search engines. A fair amount of user queries seek information on problem-solving tasks such as building a fence or repairing a bicycle. However, knowledge graphs completely lack this kind of how-to… more
  • Domain-Targeted, High Precision Knowledge Extraction

    Bhavana Dalvi, Niket Tandon, and Peter ClarkTACL2017 Our goal is to construct a domain-targeted, high precision knowledge base (KB), containing general (subject,predicate,object) statements about the world, in support of a downstream question-answering (QA) application. Despite recent advances in information… more
  • End-to-End Neural Ad-hoc Ranking with Kernel Pooling

    Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, and Russell PowerSIGIR2017 This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to… more
  • End-to-end Neural Coreference Resolution

    Kenton Lee, Luheng He, Mike Lewis, and Luke ZettlemoyerEMNLP2017 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 handengineered mention detector. The key idea is to directly consider all spans in a document as… more
All Projects
All Years