Skip to main content
×
Home
    • Aa
    • Aa

Parallel and nested decomposition for factoid questions

  • BRANIMIR BOGURAEV (a1), SIDDHARTH PATWARDHAN (a1), ADITYA KALYANPUR (a1), JENNIFER CHU-CARROLL (a1) and ADAM LALLY (a1)...
Abstract
Abstract

Typically, automatic Question Answering (QA) approaches use the question in its entirety in the search for potential answers. We argue that decomposing complex factoid questions into separate facts about their answers is beneficial to QA, since an answer candidate with support coming from multiple independent facts is more likely to be the correct one. We broadly categorize decomposable questions as parallel or nested, and we present a novel question decomposition framework for enhancing the ability of single-shot QA systems to answer complex factoid questions. Essential to the framework are components for decomposition recognition, question rewriting, and candidate answer synthesis and re-ranking. We discuss the interplay among these, with particular emphasis on decomposition recognition, a process which, we argue, can be sufficiently informed by lexico-syntactic features alone. We validate our approach to decomposition by implementing the framework on top of IBM Watson™, a state-of-the-art QA system, and showing a statistically significant improvement over its accuracy.

Copyright
Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

Q. McNemar , 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12 (2): 153–7.

Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Natural Language Engineering
  • ISSN: 1351-3249
  • EISSN: 1469-8110
  • URL: /core/journals/natural-language-engineering
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Metrics

Full text views

Total number of HTML views: 1
Total number of PDF views: 9 *
Loading metrics...

Abstract views

Total abstract views: 415 *
Loading metrics...

* Views captured on Cambridge Core between September 2016 - 23rd March 2017. This data will be updated every 24 hours.