Chinese QA and CLQA: NTCIR-5 QA Experiments at UNT Metadata

Metadata describes a digital item, providing (if known) such information as creator, publisher, contents, size, relationship to other resources, and more. Metadata may also contain "preservation" components that help us to maintain the integrity of digital files over time.

Title

  • Main Title Chinese QA and CLQA: NTCIR-5 QA Experiments at UNT

Creator

  • Author: Chen, Jiangping
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Li, Rowena
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Yu, Ping
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Ge, He
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Chin, Pok
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Li, Fei
    Creator Type: Personal
    Creator Info: University of North Texas
  • Author: Xuan, Cong
    Creator Type: Personal
    Creator Info: University of North Texas

Contributor

  • Organizer of meeting: National Institute of Informatics
    Contributor Type: Organization

Date

  • Creation: 2005-12

Language

  • English

Description

  • Content Description: This paper describes our participation in the NTCIR-5 CLQA task.
  • Physical Description: 8 p.

Subject

  • Keyword: Chinese Question Answering
  • Keyword: Cross Language Question Answering
  • Keyword: natural language processing
  • Keyword: system development

Source

  • Conference: Fifth NTCIR-5 Workshop Meeting, 2005, Tokyo, Japan

Collection

  • Name: UNT Scholarly Works
    Code: UNTSW

Institution

  • Name: UNT College of Information
    Code: UNTCOI

Rights

  • Rights Access: public

Resource Type

  • Paper

Format

  • Text

Identifier

  • Archival Resource Key: ark:/67531/metadc96830

Degree

  • Academic Department: Library and Information Science

Note

  • Display Note: Abstract: This paper describes our participation in the NTCIR-5 CLQA task. Three runs were officially submitted for three subtasks: Chinese Question Answering, English-Chinese Question Answering, and Chinese-English Question Answering. We expanded their TREC experimental QA system EagleQA this year to include Chinese QA and Cross-Language QA capabilities. Various information retrieval and natural language processing tools were incorporated with their home-built programs such as Answer Type Identification, Sentence Extraction, and Answer Finding to find answers to the test questions. Future development will focus on investigating effective question translation and answer finding solutions.