arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.06155cs.CL
收藏

一种基于人物角色的神经会话模型

A Persona-Based Neural Conversation Model

Stanford University(斯坦福大学);Microsoft Research(微软研究院);University College London(伦敦大学学院)

Jiwei Li, Michel Galley, Chris Brockett, Georgios P. Spithourakis, Jianfeng Gao, Bill Dolan

摘要:

我们提出了基于人物的模型来处理神经反应生成中的说话人一致性问题。说话人模型将人物角色编码到分布式嵌入中,这些嵌入捕获了个人特征,如背景信息和说话风格。一个二元的说话人-受话人模型捕捉两个对话者之间的互动属性。我们的模型在困惑和BLEU分数方面都比基线序列到序列模型产生了定性的性能改进,并且在说话者一致性方面具有类似的增益,如由人类判断所测量的。

英文摘要:

We present persona-based models for handling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed embeddings that capture individual characteristics such as background information and speaking style. A dyadic speaker-addressee model captures properties of interactions between two interlocutors. Our models yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models, with similar gains in speaker consistency as measured by human judges.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑