Corpus ID: 20638934

Question Answering as Global Reasoning Over Semantic Abstractions

  title={Question Answering as Global Reasoning Over Semantic Abstractions},
  author={Daniel Khashabi and Tushar Khot and A. Sabharwal and D. Roth},
  • Daniel Khashabi, Tushar Khot, +1 author D. Roth
  • Published in AAAI 2018
  • Computer Science
  • We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. [...] Key Method Representing multiple abstractions as a family of graphs, we translate question answering (QA) into a search for an optimal subgraph that satisfies certain global and local properties. This formulation generalizes several prior structured QA systems. Our system, SEMANTICILP, demonstrates strong performance on two domains simultaneously. In particular, on a collection of challenging…Expand Abstract
    46 Citations
    Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds
    • 7
    • PDF
    QASC: A Dataset for Question Answering via Sentence Composition
    • 29
    • PDF
    Robust Question Answering Through Sub-part Alignment
    Keyword-Attentive Deep Semantic Matching
    Improving Question Answering with External Knowledge
    • 22
    • PDF
    Extracting Common Inference Patterns from Semi-Structured Explanations
    • 1
    • PDF
    A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset
    • 19
    • PDF
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
    • 149
    • PDF
    Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
    • 1
    • PDF


    Question Answering via Integer Programming over Semi-Structured Knowledge
    • 71
    • PDF
    Mapping Dependencies Trees: An Application to Question Answering
    • 92
    • PDF
    ILLINOIS-PROFILER: Knowledge Schemas at Scale
    • 3
    • PDF
    Answering Complex Questions Using Open Information Extraction
    • 64
    • PDF
    Using Semantic Roles to Improve Question Answering
    • 384
    • PDF
    Knowledge-Based Textual Inference via Parse-Tree Transformations
    • 7
    • PDF
    Question Answering over Freebase with Multi-Column Convolutional Neural Networks
    • 272
    • PDF
    Combining semantic information in question answering systems
    • 51
    Modeling Biological Processes for Reading Comprehension
    • 135
    • Highly Influential
    • PDF
    The Importance of Syntactic Parsing and Inference in Semantic Role Labeling
    • 391
    • PDF