In this paper, we present a learning approach to the scenario template task of information extraction, where information filling one template could come from multiple sentences. ...
Word graphs are able to represent a large number of different utterance hypotheses in a very compact manner. However, usually they contain a huge amount of redundancy in terms of ...
This paper describes novel and practical Japanese parsers that uses decision trees. First, we construct a single decision tree to estimate modification probabilities; how one phra...
This paper describes a system that performs hierarchical error repair for illformed sentences, with heterarchical control of chart items produced at the lexical, syntactic, and se...
Determining the attachments of prepositions and subordinate conjunctions is a key problem in parsing natural language. This paper presents a trainable approach to making these att...