• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Intelligent Information Systems >Towards portable natural language interfaces based on case-based reasoning
【24h】

Towards portable natural language interfaces based on case-based reasoning

机译：基于事例推理的可移植自然语言界面

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Natural Language Interfaces allow non-technical people to access information stored in Knowledge Bases keeping them unaware of the particular structure of the model or the underlying formal query language. Early research in the field was devoted to improve the performance of a particular system for a given Knowledge Base. Since adapting the system to new domains usually entailed considerable effort, investigating how to bring Portability to NLI became a new challenge. In this article, we investigate how Case-Based Reasoning could serve to assist the expert in porting the system so as to improve its retrieval performance. Our method HITS is based on a novel grammar learning algorithm combined with language acquisition techniques that exploit structural analogies. The learner (system) is able to engage the teacher (expert) with clarification dialogues to validate conjectures (hypotheses and deductions) about the language. Our method presents the following advantages: (i) the customization is naturally defined in the case-based cycle, (ii) the types of questions the system can deal with are not delimited in advance, and (iii) the system 'reasons' about precedent cases to deal with unseen questions.
机译：自然语言界面允许非技术人员访问存储在知识库中的信息，从而使他们不知道模型的特定结构或基础形式的查询语言。该领域的早期研究致力于改善给定知识库的特定系统的性能。由于使系统适应新领域通常需要付出大量努力，因此研究如何将可移植性引入NLI成为了新的挑战。在本文中，我们研究基于案例的推理如何帮助专家移植系统，从而提高其检索性能。我们的方法HITS基于一种新颖的语法学习算法，结合了利用结构类比的语言习得技术。学习者（系统）能够与教师（专家）进行澄清对话，以验证关于语言的猜想（假设和推论）。我们的方法具有以下优点：（i）自定义是在基于案例的周期中自然定义的；（ii）系统可以处理的问题的类型没有预先确定，并且（iii）系统“关于”的原因处理未见问题的先例。

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