arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.07972cs.CLcs.AI
收藏

一种基于反思机制的多轮机器阅读理解框架--推理-原因对抽取

A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction

Southeast Academy of Information Technology(东南信息技术研究院);Beijing Institute of Technology(北京理工大学)

Changzhi Zhou, Dandan Song, Jing Xu, Zhijing Wu

摘要:

情感-原因对提取(ECPE)是情感原因分析中的一个新兴任务,它从情感文档中提取潜在的情感-原因对。最近的研究使用端到端的方法来解决ECPE任务。然而,这些方法要么遭受标签稀疏性问题,要么无法对情绪和原因之间的复杂关系进行建模。此外,它们都没有考虑小句的显式语义信息。为此,我们将ECPE任务转化为文档级的机器阅读理解(MRC)任务,并提出了一个带有反思机制的多轮MRC框架(MM-R)。我们的框架可以模拟情感和原因之间的复杂关系,同时避免生成配对矩阵(标签稀疏性问题的主要原因)。此外,多话轮结构还可以融合情感和原因之间的显性语义信息流。在基准情感原因语料库上进行的大量实验证明了我们提出的框架的有效性,它优于现有的最先进的方法。

英文摘要:

Emotion-cause pair extraction (ECPE) is an emerging task in emotion cause analysis, which extracts potential emotion-cause pairs from an emotional document. Most recent studies use end-to-end methods to tackle the ECPE task. However, these methods either suffer from a label sparsity problem or fail to model complicated relations between emotions and causes. Furthermore, they all do not consider explicit semantic information of clauses. To this end, we transform the ECPE task into a document-level machine reading comprehension (MRC) task and propose a Multi-turn MRC framework with Rethink mechanism (MM-R). Our framework can model complicated relations between emotions and causes while avoiding generating the pairing matrix (the leading cause of the label sparsity problem). Besides, the multi-turn structure can fuse explicit semantic information flow between emotions and causes. Extensive experiments on the benchmark emotion cause corpus demonstrate the effectiveness of our proposed framework, which outperforms existing state-of-the-art methods.

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。

↑