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

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.

Creator(s):
Creation Date: November 2001
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 869
Past 30 days: 15
Yesterday: 1
Creator (Author):
Harabagiu, Sanda M.

Southern Methodist University; Language Computer Corporation

Creator (Author):
Moldovan, Dan I.

Southern Methodist University; Language Computer Corporation

Creator (Author):
Paşca, Marius. 1974-

Southern Methodist University; Language Computer Corporation

Creator (Author):
Surdeanu, Mihai

Southern Methodist University; Language Computer Corporation

Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas; Southern Methodist University

Creator (Author):
Gîrju, Corina R.

Southern Methodist University

Creator (Author):
Rus, Vasile

Southern Methodist University

Creator (Author):
Lăcătuşu, Finley

Southern Methodist University

Creator (Author):
Morărescu, Paul

Southern Methodist University

Creator (Author):
Bunescu, Răzvan

Southern Methodist University

Publisher Info:
Place of Publication: [Gaithersburg, Maryland]
Date(s):
  • Creation: November 2001
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.

Degree:
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.

Physical Description:

7 p.

Language(s):
Subject(s):
Keyword(s): question answering servers | inference mechanisms | variable degrees | Language Computer Corporation
Source: Tenth Text Retrieval Conference, 2001, Gaithersburg, Maryland, United States
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc83297
Resource Type: Paper
Format: Text