Knowledge-based question answering

Fabio Rinaldi*, James Dowdall, Michael Hess, Diego Mollá, Rolf Schwitter, Kaarel Kaljurand

*Corresponding author for this work

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Large amounts of technical documentation are available in machine readable form, however there is a lack of effective ways to access them. In this paper we propose an approach based on linguistic techniques, geared towards the creation of a domain-specific Knowledge Base, starting from the available technical documentation. We then discuss an effective way to access the information encoded in the Knowledge Base. Given a user question phrased in natural language the system is capable of retrieving the encoded semantic information that most closely matches the user input, and present it by highlighting the textual elements that were used to deduct it.

Original languageEnglish
Pages (from-to)785-792
Number of pages8
JournalLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume2773 PART 1
Publication statusPublished - 2003

Fingerprint Dive into the research topics of 'Knowledge-based question answering'. Together they form a unique fingerprint.

Cite this