Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3707–3717 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 3707 Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction Chuang Fan1, Chaofa Yuan1, Jiachen Du1, Lin Gui2∗, Min Yang3, Ruifeng Xu1,4,5∗ 1Harbin Institute of Technology (Shenzhen), China 2University of Warwick, UK 3Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 4Joint Lab of Harbin Institute of Technology and RICOH, 5Peng Cheng Laboratory {fanchuanghit, bruceyuan123, jacobvan199165}@gmail.com Lin.Gui@warwick.ac.uk, min.yang@siat.ac.cn, xuruifeng@hit.edu.cn Abstract Emotion-cause pair extraction aims to extract all potential pairs of emotions and correspond- ing causes from unannotated emotion text. Most existing methods are pipelined frame- work, which identifies emotions and extracts causes separately, leading to a drawback of er- ror propagation. Towards this issue, we pro- pose a transition-based model to transform the task into a procedure of parsing-like directed graph construction. The proposed model in- crementally generates the directed graph with labeled edges based on a sequence of ac- tions, from which we can recognize emotions with the corresponding causes simultaneously, thereby optimizing separate subtasks jointly and maximizing mutual benefits of tasks inter- dependently. Experimental results show that our approach achieves the best performance, outperforming the state-of-the-art methods by 6.71% (p < 0.01) in F1 measure. 1 Introduction Emotion-cause pair extraction (ECPE) is a new task to identify emotions and the corresponding causes from unannotated emotion text (Xia and Ding, 2019). This involves several subtasks, in- cluding 1) Extracting pair components from input text, e.g., emotion detection and cause detection; 2) Combining all the elements of the two sets into emotion-cause pairs and eliminating the pairs that do not exist a causal relationship. For the former subtask, a clause can be categorized into “emo- tion”, which usually contains an emotion keyword to express specific sentiment polarity, or “cause”, which contains the reason or stimuli of an observed emotion. Then, the set of all possible emotion- cause pairs will be fed into the second subtask to determine the relationship. In general, it is an es- sential issue in emotion analysis since it provides ∗ Co-Corresponding Authors Figure 1: An example of emotion-cause pair extraction. a new perspective to investigate how emotions are provoked, expressed, and perceived. Figure 1 shows an example of ECPE, and the text is segmented into three clauses. In this instance, only the second clause and the third clause hold an emotion causality, where “I lost my phone while shopping” is the cause of emotion “ I feel sad now”. Thus, the extracted results of this sample should be {I lost my phone while shopping, I feel sad now}. The goal of ECPE is to identify all the pairs that have emotion causality in an emotion text. However, from both theoretical and computa- tional perspectives, due to the inherent ambiguity and subtlety of emotions, it is hard for machines to build a mechanism for understanding emotion causality like human beings. Previous approaches mostly focused on detecting the causes towards the given annotation of emotions, …

Content truncated to 500 words