Summary: Towards Answer Extraction:
An Application to Technical Domains
Fabio Rinaldi  and James Dowdall  and Michael Hess  and Diego Moll’ a y and Rolf Schwitter y
Abstract. The shortcomings of traditional Information Retrieval
are most evident when users require exact information rather than
relevant documents. This practical need is pushing the research com­
munity towards systems that can exactly pinpoint those parts of
documents that contain the information requested. Answer Extrac­
tion (AE) systems aim to satisfy this need. This paper presents one
such system (ExtrAns) which works by transforming documents and
queries into a semantic representation called Minimal Logical Form
(MLF) and derives the answers by logical proof from the documents.
MLFs use underspecification to overcome the problems associated
with a complete semantic representation and offer the possibility of
monotonic, non­destructive extension.
1 Introduction
The classical type of `information need' solved by existing Informa­
tion Retrieval (IR) applications has a number of shortcomings which
new techniques such as Information Extraction and Answer Extrac­
tion aim at solving. Traditionally, it is assumed that IR systems have

Source: Aliod, Diego Mollá - Department of Computing, Macquarie University

Collections: Computer Technologies and Information Sciences