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 community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (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, non-destructive extension.