Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
The system achieves conceptual generation using a discourse schema system [McKnent selects items from a knowledge base and orders them ewon 1985, Paris 1985]; stylistic generation will be ruleinto a message to address some discourse goal. This mes- based. The revision component will review the generated sage is passed to the stylistic component that makes lex- text and produce recommendations to the conceptual and ical and syntactic choices to produce a natural language stylistic components as to how to improve the text. . | Conceptual Revision for Natural Language Generation Ben E. Cline Department of Computer Science Blacksburg VA 24061 benjy@vtvml .cc.vt.edu Traditional natural language generation systems are based on a pipelined architecture. A conceptual component selects items from a knowledge base and orders them into a message to address some discourse goal. This message is passed to the stylistic component that makes lexical and syntactic choices to produce a natural language surface text. By contrast humans producing formal text typically create drafts which they polish through revision Hayes and Flower 1980 . One proposal for improving the quality of computer-generated multisentential text is to incorporate a draft-and-revision paradigm. Some researchers have suggested that revision in generation systems should only affect stylistic elements of the text Vaughan and McDonald 1986 . But human writers also engage in conceptual revision and there is reason to believe that techniques for conceptual revision should also be useful for a generation system producing formal text. Yazdani 1987 argues that both stylistic and conceptual revisions are useful. This paper extends those arguments and provides further evidence for the usefulness of conceptual as well as stylistic revision. We present strategies for identifying situations applicable to conceptual revision and techniques for effecting the revision. Why is revision important for a natural language generation system First Hayes and Flower suggest that revision reduces the cognitive strain of an author by postponing the need to make some decisions while concentrating on others. A generation system can reduce complexity in the same way. By using revision generation modules can be simpler. Second inspection of surface text is necessary to determine whether the generated text is ambiguous. Ambiguities result not only from the words used at the surface level but from their relationships to other words in the text. To detect .
