| 面向图书馆数字参考咨询的人机对话模型 |
| |
| 引用本文： | 朱娜娜,景东,张智钧.面向图书馆数字参考咨询的人机对话模型[J].图书情报工作,2019,63(6):5-11. |
| |
| 作者姓名： | 朱娜娜 景东 张智钧 |
| |
| 作者单位： | 1. 哈尔滨学院图书馆 哈尔滨 150001;
2. 黑龙江大学信息管理学院 哈尔滨 150001;
3. 哈尔滨工业大学机电工程学院 哈尔滨 150001 |
| |
| 基金项目： | 本文系国家社会科学基金项目"社交媒体突发公共事件的协同应急机制研究"（项目编号：14CXW045）和2018年黑龙江大学研究生学术交流项目"基于深度学习的开放数据与数据安全政策协同度判定"研究成果之一。 |
| |
| 摘 要： | 目的/意义]针对现有图书馆数字参考咨询人机对话机器人在对话回复内容方面的局限,提出一种融合人物画像的对话生成模型,使其回复更具个性化和趣味性,以提升图书馆智能咨询服务效果.方法/过程]利用人机对话技术,对图书馆数字参考咨询服务中的用户和问题进行自动建模,建模方式分为个性化回复风格建模和特定用户属性建模。在个性化回复风格建模上,提出一种基于对话表示和相关性回复建模方法,该方法在学习到对话相关性的同时,利用个性化文本生成个性化的回复;在用户个人属性建模方面,基于信息抽取技术生成用户的人物画像。结果/结论]实验结果表明,所提出的个性化回复生成模型优于已有的回复生成模型,人物画像识别的F值达到了 99.8%。
|
| 关 键 词： | 人机对话 数字参考咨询 智能图书馆 |
| 收稿时间： | 2018-07-03 |
A Human-Computer Dialogue Model for Digital Reference Consultation in Library |
| |
| Zhu Nana,Jing Dong,Zhang Zhijun.A Human-Computer Dialogue Model for Digital Reference Consultation in Library[J].Library and Information Service,2019,63(6):5-11. |
| |
| Authors: | Zhu Nana Jing Dong Zhang Zhijun |
| |
| Institution: | 1. Harbin University Library, Harbin 150001;
2. School of Information Management, Heilongjiang University, Harbin 150001;
3. School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001 |
| |
| Abstract: | Purpose/significance] In view of the limits of response generation of conversational robots in the existing in library digital reference, this paper proposes a dialogue generation model which integrates the portraits of characters, making the reply more personalized and interesting, in order to improve the effect of library intelligent reference service.Method/process] We automatically model the specific roles and questions in digital reference service of library in two separate ways. First is to model the personalized responding style of specific role and second is to model the aspects of the role. In modeling personalized responding style, we propose an utterance representation and responding relevance-based approach to simultaneously learn the relevance of dialogue and utilize the personalized text to generate personalized responses. In modeling aspects of a specific role, we establish human profile by employing the information extraction techniques. Result/conclusion] The experimental results show that, the personalized reply generation model proposed by us is superior to the best one, and the F score of user profiling recognition is 99.8%. |
| |
| Keywords: | human-computer dialogue digital reference service smart library |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《图书情报工作》浏览原始摘要信息 |
| 点击此处可从《图书情报工作》下载免费的PDF全文 |
|
