论文信息 - Building Natural-Language Generation Systems

Building Natural-Language Generation Systems

Natural Language Generation (NLG) systems generate texts in English (or other human languages, such as French) from computer-accessible data. NLG systems are (currently) most often used to help human authors write routine documents, including business letters [SBW91] and weather reports [GDK94]. They also have been used as interactive explanation tools which communicate information in an understandable way to non-expert users, especially in software engineering (eg, [RK92]) and medical (eg, [BMF94]) contexts. From a technical perspective, almost all applied NLG systems perform the following three tasks [Rei94]:

Ehud Reiter

[1] John Levine,et al. Automatic generation of technical documentation , 1994, Appl. Artif. Intell..

[2] Ehud Reiter,et al. Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible? , 1994, INLG.

[3] R. Kittredge,et al. Using natural-language processing to produce weather forecasts , 1994, IEEE Expert.

[4] Michael Elhadad,et al. Using argumentation to control lexical choice: a functional unification implementation , 1993 .

[5] Owen Rambow,et al. Applied Text Generation , 1992, ANLP.

[6] Guy Lapalme,et al. Text generation , 1990 .

[7] Eduard H. Hovy,et al. Planning Coherent Multisentential Text , 1988, ACL.

[8] Stephen Springer,et al. Automatic Letter Composition for Customer Service , 1991, IAAI.