arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.08587cs.CL
收藏

使用多个Token、段和上下文信息表示的深度对话行为识别

Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations

INESC-ID(INESC-ID(里斯本高等工程系统与计算机研究所));Instituto Superior Técnico, Universidade de Lisboa(里斯本大学高等技术学院);Instituto Universitário de Lisboa (ISCTE-IUL)(里斯本大学学院(ISCTE-IUL))

Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos

摘要:

对话行为(DA)识别是多年来被广泛探索的任务。最近,大多数任务的方法探索了不同的DNN架构,以组合片段中单词的表示,并生成提供意图提示的片段表示。在这项研究中,我们探索的手段,以产生更多的信息段表示,不仅通过探索不同的网络架构,但也考虑到不同的令牌表示,不仅在字的水平,但也在字符和功能水平。在词的层面上,除了常用的uncontextualized嵌入,我们探讨了使用contextualized表示,提供有关词义和段结构的信息。词汇级标记化对于捕获无法在单词级捕获的与意图相关的形态方面很重要。最后,功能层提供了一个词的抽象,它将焦点转移到段的结构上。我们还探讨了方法,以丰富的段表示与上下文信息的历史对话,无论是在分类的周围段和话轮转换的历史。在以往的研究中,这类信息已经被证明对DA的消歧非常重要。然而,我们能够通过考虑对话历史的摘要和更广泛的话轮转换上下文来捕获额外的信息。通过在每个步骤中结合最佳方法,我们在SwDA和MRDA这两个最广泛探索的语料库上实现了超越先前最先进的通用DA识别的结果。此外,通过考虑过去和未来的背景下,模拟注释场景,我们的方法实现了类似的人类注释器在SwDA上的性能,并超过它在MRDA上。

英文摘要:

Dialog act (DA) recognition is a task that has been widely explored over the years. Recently, most approaches to the task explored different DNN architectures to combine the representations of the words in a segment and generate a segment representation that provides cues for intention. In this study, we explore means to generate more informative segment representations, not only by exploring different network architectures, but also by considering different token representations, not only at the word level, but also at the character and functional levels. At the word level, in addition to the commonly used uncontextualized embeddings, we explore the use of contextualized representations, which provide information concerning word sense and segment structure. Character-level tokenization is important to capture intention-related morphological aspects that cannot be captured at the word level. Finally, the functional level provides an abstraction from words, which shifts the focus to the structure of the segment. We also explore approaches to enrich the segment representation with context information from the history of the dialog, both in terms of the classifications of the surrounding segments and the turn-taking history. This kind of information has already been proved important for the disambiguation of DAs in previous studies. Nevertheless, we are able to capture additional information by considering a summary of the dialog history and a wider turn-taking context. By combining the best approaches at each step, we achieve results that surpass the previous state-of-the-art on generic DA recognition on both SwDA and MRDA, two of the most widely explored corpora for the task. Furthermore, by considering both past and future context, simulating annotation scenario, our approach achieves a performance similar to that of a human annotator on SwDA and surpasses it on MRDA.

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。

↑