This paper presents a quantitative evaluation of the portability to the stock market domain of the revision rule hierarchy used by the system STREAKto incrementally generate newsw...
We show how a general grammar may be automatically adapted for fast parsing of utterances from a specific domain by means of constituent pruning and grammar specialization based o...
In this paper, we present a new approach for word sense disambiguation (WSD) using an exemplar-based learning algorithm. This approach integrates a diverse set of knowledge source...
Context-dependent rewrite rules are used in many areas of natural language and speech processing. Work in computational phonology has demonstrated that, given certain conditions, ...
Off-line compilation of logic grammars using Magic allows an incorporation of filtering into the logic underlying the grammar. The explicit definite clause characterization of fil...
This paper discusses the problem of learning language from unprocessed text and speech signals, concentrating on the problem of learning a lexicon. In particular, it argues for a ...
We present a natural language interface system which is based entirely on trained statistical models. The system consists of three stages of processing: parsing, semantic interpre...
Scott Miller, David Stallard, Robert J. Bobrow, Ri...
Words unknown to the lexicon present a substantial problem to part-of-speech tagging. In this paper we present a technique for fully unsupervised statistical acquisition of rules ...