Question answering from structured knowledge sources

Frank, Anette, Krieger, Hans-Ulrich, Xu, Feiyu, Uszkoreit, Hans, Crysmann, Bernd, Joerg, Brigitte ORCID: https://orcid.org/0000-0001-7941-8108 and Schäfer, Ulrich (2007) Question answering from structured knowledge sources. Journal of Applied Logic, 5 (1) . pp. 20-48. ISSN 1570-8683 [Article] (doi:10.1016/j.jal.2005.12.006)

Abstract

We present an implemented approach for domain-restricted question answering from structured knowledge sources, based on robust semantic analysis in a hybrid NLP system architecture. We perform question interpretation and answer extraction in an architecture that builds on a lexical-conceptual structure for question interpretation, which is interfaced with domain-specific concepts and properties in a structured knowledge base. Question interpretation involves a limited amount of domain-specific inferences, and accounts for higher-level quantificational questions. Question interpretation and answer extraction are modular components that interact in clearly defined ways. We derive so-called proto queries from the linguistic representations, which provide partial constraints for answer extraction from the underlying knowledge sources. The search queries we construct from proto queries effectively compute minimal spanning trees from the underlying knowledge sources. Our approach naturally extends to multilingual question answering, and has been developed as a prototype system for two application domains: the domain of Nobel prize winners, and the domain of Language Technology, on the basis of the large ontology underlying the information portal LT World.

Item Type: Article
Keywords (uncontrolled): QA, Hybrid NLP, Multilinguality, RMRS, Question semantics, Ontology modeling, Data base queries
Research Areas: A. > Library and Student Support
Item ID: 26496
Useful Links:
Depositing User: Brigitte Joerg
Date Deposited: 27 Sep 2020 16:19
Last Modified: 27 Sep 2020 16:19
URI: https://eprints.mdx.ac.uk/id/eprint/26496

Actions (login required)

View Item View Item