AQUAINT: Meaning-Oriented Question-Answering
with Ontological Semantics
This project is from a team consisting of New Mexico State University's
Computing Research Laboratory (CRL) of Las Cruces, NM, the Institute for
Language and Information Technologies, University of Maryland Baltimore
County (ILIT), and CoGenTex.
team proposes a comprehensive system-level effort covering all three
main technical areas:
- question understanding and interpretation;
- determining the answer;
- presenting the answer.
The first complete version of the proposed system will concentrate
on answering questions about travel and meetings, and will use two kinds
of data sources:
- open text (in English, Arabic and one of Persian, Russian or Spanish,
selected in consultation with ARDA);
- a structured database, called a fact database (Fact DB),
whose entries are instances of concepts in the system's ontology,
or world model.
The Fact DB, the ontology and the lexicons for the three languages,
together with the working memory that includes the intermediate results
of the system's operation, are the major static knowledge sources
in the proposed system.
For more information
Korelsky, Tanya; Lavoie, Benoit; and Caldwell, Ted (2003).
Ontology-based Multimodal User Interface in MOQA.
In Proceedings of the AQUAINT 18-Month Workshop,
San Diego, California.
[PowerPoint, 848 Kb]
Beale, Stephen; Lavoie, Benoit; McShane, Marjorie; Nirenburg, Sergei; and Korelsky, Tanya (2004).
Question Answering Using Ontological Semantics.
In Proceedings of the 2nd Workshop on Text Meaning and Interpretation of ACL 2004,
Barcelona, Spain, pp. 41-48.
[Acrobat, 1067 Kb]