tailieunhanh - Báo cáo khoa học: "Controlling Lexical Substitution in Computer Text Generation"

Th=s report describes Paul, a computer text generation system desig~ed LO create cohesive text through the use o| lexlcal substitutions. Specihcally, Ihas system is designed Io determmistically choose between provluminahzat0on, superordinate suhstntut0on, and dehmte noun phrase reiterabon. The system identities a strength el antecedence recovery for each of the lex~cal subshtutions, and matches them against the strength el potenfml antecedence of each element m the text to select the proper substitutions for these elements. . | Controlling Lexical Substitution in Computer Text Generation1 Robert Granville MIT Laboratory for Computer Science 545 Technology Square Cambridge. Massachusetts 02139 Abstract This report describes Paul a computer text generation system designed to create cohesive text through the use of lexical substitutions. Specifically this system is designed to deterministically choose between pronominalization. superordinate substitution and definite noun phrase reiteration. The system identifies a strength ot antecedence recovery for each of the lexical substitutions and matches them against the strength ot potential antecedence of each element in the text to select the proper substitutions for these elements. 1. Introduction This report describes Paul a computer text generation system designed to create cohesive text through the use of lexical substitutions. Spec fically. tins system IS designed to deterministically choose between pronoinmalization. suucrordinate substitution and definite noun phrase reiteration. The system identifies a strength ot antecedence recovery for each of the lexical substitutions and matches them against the strength of potential antecedence of each element in the text to select the proper substitutions for these elements. Paul is a natural language generation program initially developed at IBM s Thomas J. Watson Hesearch Center as part of the ongoing Epistle protect 5. 61. The emphasis of the the work reported here is in the research ol discourse phenomena the study of cohesion and its effects on multisentential texts 3 9 . Paul accepts as input LISP knowledge structures consisting of case frame ft formalisms representing each sentence to be generated. These knowledge structures are translated into English with the appropriate lexical substitutions being made at this time. No attempt IS made by the system to create these knowledge structures. 2. Cohesion Tire purpose of communication is for one person the speaker or writer to express her .