Answering complex, list and context questions with LCC's Question-Answering Server 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 Answering complex, list and context questions with LCC's Question-Answering Server

Creator

  • Author: Harabagiu, Sanda M.
    Creator Type: Personal
    Creator Info: Southern Methodist University; Language Computer Corporation
  • Author: Moldovan, Dan I.
    Creator Type: Personal
    Creator Info: Southern Methodist University; Language Computer Corporation
  • Author: Paşca, Marius. 1974-
    Creator Type: Personal
    Creator Info: Southern Methodist University; Language Computer Corporation
  • Author: Surdeanu, Mihai
    Creator Type: Personal
    Creator Info: Southern Methodist University; Language Computer Corporation
  • Author: Mihalcea, Rada, 1974-
    Creator Type: Personal
    Creator Info: University of North Texas; Southern Methodist University
  • Author: Gîrju, Corina R.
    Creator Type: Personal
    Creator Info: Southern Methodist University
  • Author: Rus, Vasile
    Creator Type: Personal
    Creator Info: Southern Methodist University
  • Author: Lăcătuşu, Finley
    Creator Type: Personal
    Creator Info: Southern Methodist University
  • Author: Morărescu, Paul
    Creator Type: Personal
    Creator Info: Southern Methodist University
  • Author: Bunescu, Răzvan
    Creator Type: Personal
    Creator Info: Southern Methodist University

Contributor

  • Organizer of meeting: National Institute of Standards and Technology (U.S.)
    Contributor Type: Organization

Publisher

  • Name: National Institute of Standards and Technology (U.S.)
    Place of Publication: [Gaithersburg, Maryland]

Date

  • Creation: 2001-11

Language

  • English

Description

  • Content Description: This paper presents the architecture of the Question-Answering server (QAS) developed at the Language Computer Corporation (LCC) and used in the TREC-10 evaluations.
  • Physical Description: 7 p.

Subject

  • Keyword: question answering servers
  • Keyword: inference mechanisms
  • Keyword: variable degrees
  • Keyword: Language Computer Corporation

Source

  • Conference: Tenth Text Retrieval Conference, 2001, Gaithersburg, Maryland, United States

Collection

  • Name: UNT Scholarly Works
    Code: UNTSW

Institution

  • Name: UNT College of Engineering
    Code: UNTCOE

Resource Type

  • Paper

Format

  • Text

Identifier

  • Archival Resource Key: ark:/67531/metadc83297

Degree

  • Academic Department: Computer Science and Engineering

Note

  • Display Note: Abstract: This paper presents the architecture of the Question-Answering server (QAS) developed at the Language Computer Corporation (LCC) and used in the TREC-10 evaluations. LCC's QAS™ extracts answers for (a) factual questions of variable degree of difficulty; (b) questions that expect lists of answers; and (c) questions posed in the context of previous questions and answers. One of the major novelties is the implementation of bridging inference mechanisms that guide the search for answers to complex questions. Additionally, LCC's QAS™ encodes an efficient way of modeling context via reference resolution. In TREC-10, this system generated an RAR of 0.58 on the main task and 0.78 on the context task.