A Symmetric Local Search Network for Emotion-Cause Pair Extraction

Abstract

Emotion-cause pair extraction (ECPE) is a new task which aims at extracting the potential clause pairs of emotions and corresponding causes in a document. To tackle this task, a two-step method was proposed by previous study which first extracted emotion clauses and cause clauses individually, then paired the emotion and cause clauses, and filtered out the pairs without causality. Different from this method that separated the detection and the matching of emotion and cause into two steps, we propose a Symmetric Local Search Network (SLSN) model to perform the detection and matching simultaneously by local search. SLSN consists of two symmetric subnetworks, namely the emotion subnetwork and the cause subnetwork. Each subnetwork is composed of a clause representation learner and a local pair searcher. The local pair searcher is a specially-designed cross-subnetwork component which can extract the local emotion-cause pairs. Experimental results on the ECPE corpus demonstrate the superiority of our SLSN over existing state-of-the-art methods.

Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction

“…Due to the problem of the tremendous search space, most existing methods have fully exploited relative position fea-tures to decrease the number of candidate pairs. For instance, ECPE-MLL (Ding et al, 2020b) and SLSN (Cheng et al, 2020) set a fixed size window around a certain clause, and the central clause and other clauses inside the window comprise candidate pairs. However, models heavily relying on the relative position features ignore the distant semantic cues, resulting in poor generalization ability towards position-insensitive data in which the cause clause is not in proximity to the emotion clause.…”

“…Most methods (Ding et al, 2020a;Cheng et al, 2020;Ding et al, 2020b) have set a fixed size window to reduce the number of candidate pairs according to the inherent position bias in the dataset, because of the sparsity of true emotion-cause pairs compared with candidate emotion-cause pairs. Besides, Chen et al (2020b) leveraged the relative position information explicitly in the process of pair representation learning.…”

“…This typical and widely used dataset is constructed based on an emotion cause extraction corpus (Gui et al, 2016) that contains 1,945 Chinese documents from SINA city news 2 . To obtain statistically credible results, we adopt the same data split setting (10-fold crossvalidation) used by Xia and Ding (2019), repeat the experiments 10 times, and report the average results of precision (P), recall (R), and F 1 -score (F 1 ) on the main task: emotion-cause pair extraction (ECPE), and two sub-tasks: emotion extraction (EE) and cause extraction (CE), following existing works (Xia and Ding, 2019;Ding et al, 2020b,a;Chen et al, 2020a,b;Cheng et al, 2020).…”

“…The window-constrained 2D Transformer achieved the best performance. SLSN-U (Cheng et al, 2020) extracted pairs through a process of local search which was defined by the setting of the local context window. RankCP (Wei et al, 2020) utilized kernel-based relative position embedding to enhance the clause representations obtained from inter-clause modeling module.…”

TSAM: A Two-Stream Attention Model for Causal Emotion Entailment

“…To extract emotion and its corresponding cause jointly, first put forward the Emotion-Cause Pair Extraction (ECPE) task and tackle it by a two-step method. Subsequently, many improved methods are proposed to tackle ECPE in an end2end manner (Ding et al, 2020a,b;Wei et al, 2020;Cheng et al, 2020;Chen et al, 2020a,b). However, these works mentioned above use news articles as the target corpus for ECE, which largely reduces reasoning complexity.…”