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 2104.11454cs.AI
收藏

预测、选择与生成:知识驱动的会话系统探索

Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System

Sichuan University(四川大学)

Cheng Luo, Dayiheng Liu, Chanjuan Li, Li Lu, Jiancheng Lv

摘要:

在开放域会话系统中,利用背景知识是重要但具有挑战性的。我们可以利用知识的融入使对话的生成可控,可以生成更多样化的包含真实知识的句子。本文将知识库和预训练模型相结合,提出了一个知识驱动的会话系统。该系统包括对话主题预测、知识匹配和对话生成等模块。在此基础上,研究了可能影响知识驱动对话生成的性能因素:主题粗召回算法、知识选择个数、生成模式选择等,这些实验结果将为今后本课题的研究提供一定的指导意义。据我们所知,这是第一个研究和分析相关因素的影响的工作。

英文摘要:

In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that contain real knowledge. In this paper, we combine the knowledge bases and pre-training model to propose a knowledge-driven conversation system. The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation. Based on this system, we study the performance factors that maybe affect the generation of knowledge-driven dialogue: topic coarse recall algorithm, number of knowledge choices, generation model choices, etc., and finally made the system reach state-of-the-art. These experimental results will provide some guiding significance for the future research of this task. As far as we know, this is the first work to study and analyze the effects of the related factors.

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。

↑