arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.10710cs.CL
收藏

通过学习链接的端到端预防原因对提取

End-to-end Emotion-Cause Pair Extraction via Learning to Link

Beijing Institute of Technology(北京理工大学);University of Padua(帕多瓦大学)

Haolin Song, Chen Zhang, Qiuchi Li, Dawei Song

摘要:

情感-原因对抽取(ECPE)是一项新兴的自然语言处理任务,旨在联合研究文档中的情感及其潜在原因。它扩展了以前的情感原因提取(ECE)的任务,但不需要一组预先给定的情感条款,在ECE。现有的ECPE方法通常采用两阶段方法,即,(1)情感和原因检测,以及(2)将检测到的情感和原因配对。这种流水线方法虽然直观,但存在两个关键问题,包括可能阻碍有效性的跨阶段误差传播,以及限制该方法实际应用的高计算成本。为了解决这些问题,我们提出了一个多任务学习模型,可以提取情绪,原因和情绪-原因对同时在一个端到端的方式。具体来说,我们的模型将对提取视为链接预测任务,并学习从情感子句到原因子句的链接,即,链路是定向的。情感提取和原因提取作为辅助任务被纳入模型,这进一步促进了对提取。在ECPE基准测试数据集上进行了实验。结果表明,我们提出的模型优于一系列最先进的方法。

英文摘要:

Emotion-cause pair extraction (ECPE), as an emergent natural language processing task, aims at jointly investigating emotions and their underlying causes in documents. It extends the previous emotion cause extraction (ECE) task, yet without requiring a set of pre-given emotion clauses as in ECE. Existing approaches to ECPE generally adopt a two-stage method, i.e., (1) emotion and cause detection, and then (2) pairing the detected emotions and causes. Such pipeline method, while intuitive, suffers from two critical issues, including error propagation across stages that may hinder the effectiveness, and high computational cost that would limit the practical application of the method. To tackle these issues, we propose a multi-task learning model that can extract emotions, causes and emotion-cause pairs simultaneously in an end-to-end manner. Specifically, our model regards pair extraction as a link prediction task, and learns to link from emotion clauses to cause clauses, i.e., the links are directional. Emotion extraction and cause extraction are incorporated into the model as auxiliary tasks, which further boost the pair extraction. Experiments are conducted on an ECPE benchmarking dataset. The results show that our proposed model outperforms a range of state-of-the-art approaches.

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。

↑