tailieunhanh - Báo cáo khoa học: "LINGUISTICALLY MOTIVATED DESCRIPTIVE TERM SELECTION"

A linguistically motivated approach to indexing, that is the provision of descriptive terms for texts of any kind, is presented and illustrated. The approach is designed to achieve good, . accurate and flexible, indexing by identifying index term sources in the meaning representations built by a powerful general purpose analyser, and providing a range of text expressions constituting semantic and syntactic variants for each term concept. Indexing is seen as a legitimate form of shallow text processing, but one requiring serious semantically based language processing, particularly to obtain well-founded complex terms, which is the main objective of the. | LINGUISTICALLY MOTIVATED DESCRIPTIVE TERM SELECTION K. Sparck Jones and . Tait Computer Laboratory University of Cambridge Corn Exchange street Cambridge CB2 3QG . ABSTRACT A linguistically motivated approach to indexing that is the provision of descriptive terms for texts of any kind is presented and illustrated. The approach is designed to achieve good . accurate and flexible indexing by identifying index term sources in the meaning representations built by a powerful general purpose analyser and providing a range of text expressions constituting semantic and syntactic variants for each term concept. Indexing is seen as a legitimate form of shallow text processing but one requiring serious semantically based language processing particularly to obtain well-founded complex terms which is the main objective of the project described. The type of indexing strategy described is further seen as having utility in a range of applications environments. I INDEXING NEEDS Indexing terms are required for a variety of purposes in a variety of contexts. Much effort has gone into indexing and more especially automatic indexing for conventional document retrieval but the extension of automation . in the area of office systems implies a wider need for effective Indexing and preferably for effective automatic indexing. Providing index descriptions for access to documents is not necessarily moreover a poor substitute for fully understanding documents and incorporating their contents into knowledge bases. Indexing has its own proper function and hence utility and can be successfully done without deep understanding of the texts being processed. Insofar as access to documents is by way of an explicit textual representation of a user s information need . a request this has also to be indexed and the retrieval problem is selecting relevant documents when matching request and document term descriptions. Though retrieval experiments hitherto have shown that better indexing on