Extracting Exact Answers to Questions Based on Structural Links

Abstract

This paper presents a novel approach to extracting phrase-level answers in a question answering system. This approach uses structural support provided by an integrated Natural Language Processing (NLP) and Information Extraction (IE) system. Both questions and the sentence-level candidate answer strings are parsed by this NLP/IE system into binary dependency structures. Phrase-level answer extraction is modelled by comparing the structural similarity involving the question-phrase and the candidate answer phrase. There are two types of structural support. The first type involves predefined, specific entity associations such as Affiliation, Position, Age for a person entity. If a question asks about one of these associations, the answer-phrase can be determined as long as the system decodes such pre-defined dependency links correctly, despite the syntactic difference used in expressions between the question and the candidate answer string.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2002
Accession Number
ADA457785

Entities

People

  • Cheng Niu
  • M. Srikanth
  • Rohini K. Srihari
  • Wei Li
  • Xiaoge Li
  • Xiuhong Zhang

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Acquisition
  • Air Force
  • Air Force Research Laboratories
  • Extraction
  • Grammars
  • Identification
  • Identification Systems
  • Language
  • Military Research
  • Natural Language Processing
  • Natural Languages
  • Norwegian Sea
  • Nuclear Powered Submarines
  • Precision
  • Submarines
  • Template Patterns
  • Web Browsers

Readers

  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Translation