| 基于检索结果融合机制的对话生成模型 |
| |
| 引用本文： | 刘喜凯,林鸿飞,徐博,杨亮,任玉琪. 基于检索结果融合机制的对话生成模型[J]. 中文信息学报, 2021, 35(7): 134-142 |
| |
| 作者姓名： | 刘喜凯 林鸿飞 徐博 杨亮 任玉琪 |
| |
| 作者单位： | 1.大连理工大学 计算机科学与技术学院,辽宁 大连 116024;
2.认知智能国家重点实验室(科大讯飞),安徽 合肥 230088 |
| |
| 基金项目： | 国家自然科学基金(61632011);博士后科学基金(2018M641691);教育部人文社会科学基金(19YJCZH199);认知智能国家重点实验室开放基金(COGOS-20190001) |
| |
| 摘 要： | 对话生成模型是对话系统中十分重要的组件.传统的对话生成模型仅利用用户的输入信息生成回复,这导致在生成过程中常会出现无意义的万能回复.最近有工作尝试将检索的方法融入生成模型从而提高模型的生成质量,但这些方法往往将重点放在如何编辑检索结果上,没有考虑检索结果与用户查询之间的语义空间差别.为解决这一问题,该文提出了基于检索结...
|
| 关 键 词： | 对话生成 信息检索 长短时记忆网络 融合机制 |
| 收稿时间： | 2019-09-09 |
Response Generation by Retrieved Response Fusion Mechanism |
| |
| LIU Xikai,LIN Hongfei,XU Bo,YANG Liang,REN Yuqi. Response Generation by Retrieved Response Fusion Mechanism[J]. Journal of Chinese Information Processing, 2021, 35(7): 134-142 |
| |
| Authors: | LIU Xikai LIN Hongfei XU Bo YANG Liang REN Yuqi |
| |
| Affiliation: | 1.School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning 116024, China;2.State Key Laboratory of Cognitive Intelligence, iFLYTEK, Hefei, Anhui 230088, China |
| |
| Abstract: | Response generation is an important component of the dialogue system. To better combine the retrieval-based model with a generation-based model, this paper proposes a response generative model via the retrieved response fusion mechanism. The model uses bidirectional LSTM to encode the retrieved response, and then this paper proposes a Long Short-Term Memory network with a fusion mechanism (fusion-LSTM). This mechanism fuses retrieval results with dialogue text within the model to better integrate the retrieved information into the generative model. The experimental results show that this method is superior to the baseline methods in both automatic and human evaluation. |
| |
| Keywords: | response generation information retrieval long short-term memory network fusion mechanism |
|
| 点击此处可从《中文信息学报》浏览原始摘要信息 |
|
点击此处可从《中文信息学报》下载全文 |
|
