Can We Make Information Extraction More Adaptive?

It seems widely agreed that IE (Information Extraction) is now a tested language technology that has reached precision+recall values that put it in about the same position as Information Retrieval and Machine Translation , both of which are widely used commercially. There is also a clear range of practical applications that would be eased by the sort of template-style data that IE provides. The problem for wider deployment of the technology is adaptability: the ability to customize IE rapidly to new domains. In this paper we discuss some methods that have been tried to ease this problem, and to create something more rapid than the benchmark one-month gure, which was roughly what ARPA teams in IE needed to adapt an existing system by hand to a new domain of corpora and templates. An important distinction in discussing the issue is the degree to which a user can be assumed to know what is wanted, to have pre-existing templates ready to hand, as opposed to a user who has a vague idea of what is needed from a corpus. We shall discuss attempts to derive templates directly from corpora; to derive knowledge structures and lexicons directly from corpora, including discussion of the recent LE project ECRAN which attempted to tune existing lexicons to new corpora. An important issue is how far established methods in Information Retrieval of tuning to a user's needs with feedback at an interface can be transferred to IE.