Emotion-Cause Pair Extraction as Sequence Labeling Based on A Novel Tagging Scheme

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 3568–3573, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 3568 Emotion-Cause Pair Extraction as Sequence Labeling Based on A Novel Tagging Scheme Chaofa Yuan1∗, Chuang Fan1∗, Jianzhu Bao1, Ruifeng Xu1,2,3† 1Harbin Institute of Technology (Shenzhen), China 2Peng Cheng Laboratory 3Joint Lab of Harbin Institute of Technology and RICOH {bruceyuan123, fanchuanghit, jianzhubao}@gmail.com xuruifeng@hit.edu.cn Abstract The task of emotion-cause pair extraction deals with finding all emotions and the corre- sponding causes in unannotated emotion texts. Most recent studies are based on the likeli- hood of Cartesian product among all clause candidates, resulting in a high computational cost. Targeting this issue, we regard the task as a sequence labeling problem and propose a novel tagging scheme with coding the dis- tance between linked components into the tags, so that emotions and the corresponding causes can be extracted simultaneously. Accordingly, an end-to-end model is presented to process the input texts from left to right, always with linear time complexity, leading to a speed up. Experimental results show that our proposed model achieves the best performance, outper- forming the state-of-the-art method by 2.26% (p < 0.001) in F1 measure. 1 Introduction Emotion-cause pair extraction (ECPE) aims to ex- tract all potential pairs of emotions and the corre- sponding causes from unannotated emotion texts, such as (c3, c1) and (c3, c2) in: Ex.1 A policeman visited the old man with the lost money, (c1)| and told him that the thief was caught. (c2)| The old man was very happy, (c3)| and de- posited the money in the bank. (c4) This task for pair extraction closely relates to the traditional emotion cause extraction task, which aims at identifying the causes for a given emo- tion expression. Many works (Gui et al., 2017; Li et al., 2018, 2019; Xu et al., 2019; Fan et al., 2019; Xia et al., 2019; Ding et al., 2019) related to emo- tion cause extraction have been published recently, and all of them are evaluated with the dataset re- leased by Gui et al. (2016). However, it suffers ∗ Equal Contributions. † Corresponding author. that emotions must be annotated before extracting the causes, which is labor intensive and limits the applications in real-world scenarios. Towards this issue, Xia and Ding (2019) presents a new task, namely emotion-cause pair extraction, to extract emotions and the corresponding causes together. In comparison, it is a more challenging task due to the inherent ambiguity and subtlety of emotions, especially when there is no annotation information provided before extraction. Following this task setting, they propose a two-step approach to solve this task. However, limited by the inherent drawback of pipelined framework, error propaga- tion may occur from the first procedure to the sec- ond. Recent studies (Song et al., 2020; Tang et al., 2020) have focused on solving this task using multi- task learning framework (Caruana, 1993) with well- designed attention mechanism (Bahdanau et al., 2015), but they extract emotion-cause pairs by cal- culating a …

Content truncated to 500 words