FALCON: Boosting Knowledge for Answer Engines

Description:

This paper discusses FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance.

Creator(s):
Creation Date: November 2000
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 32
Past 30 days: 3
Yesterday: 0
Creator (Author):
Harabagiu, Sanda M.

Southern Methodist University

Creator (Author):
Moldovan, Dan I.

Southern Methodist University

Creator (Author):
Paşca, Marius. 1974-

Southern Methodist University

Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas; Southern Methodist University

Creator (Author):
Surdeanu, Mihai

Southern Methodist University

Creator (Author):
Bunescu, Răzvan

Southern Methodist University

Creator (Author):
Gîrju, Corina R.

Southern Methodist University

Creator (Author):
Rus, Vasile

Southern Methodist University

Creator (Author):
Morărescu, Paul

Southern Methodist University

Date(s):
  • Creation: November 2000
Description:

This paper discusses FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance.

Degree:
Note:

Abstract: This paper presents the features of FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance. The answer engine handles question reformulations, finds the expected answer type from a large hierarchy that incorporates the WordNet semantic net and extracts answers after performing unifications on the semantic forms of the question and its candidate answers. To rule out erroneous answers, it provides justification option, implemented as an abductive proof. In TREC-9, FALCON generated a score of 58% for short answers and 76% for long answers.

Physical Description:

10 p.

Language(s):
Subject(s):
Keyword(s): answer engines | WordNet | semantic net | FALCON
Source: Ninth Annual Text Retrieval Conference (TREC), 2000, Gaithersburg, Maryland, United States
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc83296
Resource Type: Paper
Format: Text
Rights:
Access: Public