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 2004.01972cs.CL
收藏

学习一个简单有效的辅助任务多回合反应生成模型

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks

Microsoft Corporation(微软公司);Meituan(美团);Beihang University(北京航空航天大学)

Yufan Zhao, Can Xu, Wei Wu, Lei Yu

摘要:

我们研究了开放域对话的多轮响应生成。现有的最先进技术解决了深度神经架构的问题。虽然这些模型提高了响应质量,但它们的复杂性也阻碍了模型在实际系统中的应用。在这项工作中,我们追求一个模型,有一个简单的结构,但可以有效地利用会话上下文响应生成。为此,我们提出了四个辅助任务,包括词序恢复,话语顺序恢复,掩蔽词恢复,掩蔽话语恢复,并优化这些任务的目标,最大限度地提高生成的可能性。通过这种方式,与上下文理解相关的辅助任务可以指导生成模型的学习,以达到更好的局部最优。三个基准的实证研究表明,我们的模型可以显着优于国家的最先进的生成模型在自动评估和人类判断的响应质量方面,并在同一时间享有更快的解码过程。

英文摘要:

We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved response quality, their complexity also hinders the application of the models in real systems. In this work, we pursue a model that has a simple structure yet can effectively leverage conversation contexts for response generation. To this end, we propose four auxiliary tasks including word order recovery, utterance order recovery, masked word recovery, and masked utterance recovery, and optimize the objectives of these tasks together with maximizing the likelihood of generation. By this means, the auxiliary tasks that relate to context understanding can guide the learning of the generation model to achieve a better local optimum. Empirical studies with three benchmarks indicate that our model can significantly outperform state-of-the-art generation models in terms of response quality on both automatic evaluation and human judgment, and at the same time enjoys a much faster decoding process.

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。

↑