Corpus ID: 46944568

2 Matching Text to Entities : Quiz Bowl

  title={2 Matching Text to Entities : Quiz Bowl},
  author={Mohit Iyyer and Jordan L. Boyd-Graber and Leonardo Claudino and R. Socher and Hal Daum{\'e}},
  • Mohit Iyyer, Jordan L. Boyd-Graber, +2 authors Hal Daumé
  • Published 2018
  • Text classification methods for tasks like factoid question answering typically use manually defined string matching rules or bag of words representations. These methods are ineffective when question text contains very few individual words (e.g., named entities) that are indicative of the answer. We introduce a recursive neural network (rnn) model that can reason over such input by modeling textual compositionality. We apply our model, qanta, to a dataset of questions from a trivia competition… CONTINUE READING

    Figures and Tables from this paper


    Rank learning for factoid question answering with linguistic and semantic constraints
    • 53
    • PDF
    Grounded Compositional Semantics for Finding and Describing Images with Sentences
    • 703
    • PDF
    Using Semantic Roles to Improve Question Answering
    • 392
    • PDF
    Reasoning With Neural Tensor Networks for Knowledge Base Completion
    • 1,288
    • PDF
    What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA
    • 368
    • PDF
    Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
    • 4,172
    • PDF
    Zero-shot Entity Extraction from Web Pages
    • 28
    • PDF
    Distributed Representations of Sentences and Documents
    • 5,723
    • PDF
    A Survey of Answer Extraction Techniques in Factoid Question Answering
    • 45
    • PDF
    Question analysis: How Watson reads a clue
    • 155
    • PDF