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 2009.04703cs.CLcs.AI
收藏

反应选择模型真的知道下一步是什么吗?多轮应答选择的话语操纵策略

Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

Wisenut Inc.(威智努特公司);Kakao Corp.(卡卡奥公司);Korea University(高丽大学);Kakao Enterprise Corp.(卡卡奥企业公司)

Taesun Whang, Dongyub Lee, Dongsuk Oh, Chanhee Lee, Kijong Han, Dong-hun Lee, Saebyeok Lee

摘要:

在本文中,我们研究了在基于检索的多轮对话系统中,给定用户和系统话语历史选择最佳响应的任务。最近,预先训练的语言模型(例如,BERT、RoBERTa和ELECTRA)在各种自然语言处理任务中表现出显著的改进。这个和类似的响应选择任务也可以使用这样的语言模型通过将任务公式化为对话-响应二元分类任务来解决。虽然使用这种方法的现有作品成功地获得了最先进的结果,我们观察到,以这种方式训练的语言模型倾向于根据历史和候选人的相关性进行预测,忽略了多轮对话系统的顺序性。这表明,单独的响应选择任务是不够的学习话语之间的时间依赖性。为此,我们提出了话语操纵策略(UMS)来解决这个问题。具体而言,UMS由几种策略组成(即,插入、删除和搜索),这有助于响应选择模型保持对话一致性。此外,UMS是自我监督的方法,不需要额外的注释,因此可以很容易地纳入现有的方法。跨多种语言和模型的广泛评估表明,UMS在教学对话一致性方面非常有效,这导致模型在多个公共基准数据集上以显著的优势推动最先进的技术。

英文摘要:

In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and ELECTRA) showed significant improvements in various natural language processing tasks. This and similar response selection tasks can also be solved using such language models by formulating the tasks as dialog--response binary classification tasks. Although existing works using this approach successfully obtained state-of-the-art results, we observe that language models trained in this manner tend to make predictions based on the relatedness of history and candidates, ignoring the sequential nature of multi-turn dialog systems. This suggests that the response selection task alone is insufficient for learning temporal dependencies between utterances. To this end, we propose utterance manipulation strategies (UMS) to address this problem. Specifically, UMS consist of several strategies (i.e., insertion, deletion, and search), which aid the response selection model towards maintaining dialog coherence. Further, UMS are self-supervised methods that do not require additional annotation and thus can be easily incorporated into existing approaches. Extensive evaluation across multiple languages and models shows that UMS are highly effective in teaching dialog consistency, which leads to models pushing the state-of-the-art with significant margins on multiple public benchmark datasets.

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。

↑