首页> 美国政府科技报告 >Integrating Syntax, Semantics, and Discourse DARPA Natural Language Understanding Program. Volume 1. Technical Report.
【24h】

Integrating Syntax, Semantics, and Discourse DARPA Natural Language Understanding Program. Volume 1. Technical Report.

机译:整合语法,语义和话语DaRpa自然语言理解程序。第1卷。技术报告。

获取原文

摘要

Message understanding systems are key to handling the steadily increasing volume of information required for intelligence, data fusion, logistics and maintenance operations. The capture and understanding of information in narrative text and messages is the focus of this contract. The goal is to convert this information into a representation of its meaning, which can be used to update a database with new information derived from the incoming messages, to summarize key information, or to issue appropriate commands to a back-end, e.g. to query a database or an expert system. The deliverable under this contract is the PUNDIT(Prolog Understanding of Integrated Text) natural language understanding system. The PUNDIT natural language system is the most ambitious natural language understanding system built to date. Its goal in the integration of multiple linguistically-based knowledge (a domain model), to understand messages in a restricted domain. PUNDIT has been designed with portability as a major goal. To facilitate porting the system to new domains, PUNDIT maintains a careful separation of domain-independent information from domain-specific information. The system consists of a core domain-independent portion (20K lines of Prolog code) which remains constant from application to application. (KR)

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号