Proceedings

Integration of Syntactic, Semantic and Contextual Information in Processing Grammatically Ill-Formed Inputs

Osamu Imaichi, Yuji Matsumoto

Download BibTeX Cite

Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Natural Language. Pages 1435-1441.

Abstract

This paper describes an integrated method for processing grammatically ill-formed inputs. We use partial parses of the input for recovering from parsing failure. In order to select partial parses appropriate for error recovery, cost and reward are assigned to them. Cost and reward represent the badness and goodness of a partial parse, respectively. The most appropriate partial parse is selected on the basis of cost and reward trade-off. The system contains three modules. Module A handles local ill-formedness such as constraint violations. Module B handles non-local ill-formedness such as word order violations, and Module C handles non-local ill-formedness such as contextual ellipses. These three modules work in a uniform framework based on the notions of cost and reward.

Osamu Imaichi, and Yuji Matsumoto. 1995. Integration of Syntactic, Semantic and Contextual Information in Processing Grammatically Ill-Formed Inputs. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95. IJCAI, 1435–1441. https://ijcai.org/proceedings/1995/185
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards