Extracting Emotion Causes Using Learning to Rank Methods From an Information Retrieval Perspective

Abstract

Emotion cause extraction is a challenging task for the fine-grained emotion analysis. Even though a few studies have addressed the task using clause-level classification methods, most of them have partly ignored emotion-level context information. To comprehensively leverage the information, we propose a novel method based on learning to rank to identify emotion causes from an information retrieval perspective. Our method seeks to rank candidate clauses with respect to certain provoked emotions in analogy with query-level document ranking in information retrieval. To learn effective clause ranking models, we represent candidate clauses as feature vectors involving both emotion-independent features and emotion-dependent features. Emotion-independent features are extracted to capture the possibility that a clause is expected to provoke an emotion, and emotion-dependent features are extracted to capture the relevance between candidate cause clauses and their corresponding emotions. We investigate three approaches to learning to rank for emotion cause extraction in our method. We evaluate the performance of our method on an existing dataset for emotion cause extraction. The experimental results show that our method is effective in emotion cause extraction, significantly outperforming the state-of-the-art baseline methods in terms of the precision, recall, and F-measure. INDEX TERMS Emotion analysis, emotion cause extraction, natural language processing, sentiment analysis, learning to rank.

A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis

“…LambdaMART extracts emotion causes using learning to rank methods which based on the emotion-independent and emotiondependent features (Xu et al, 2019).…”

“…Recently, Gui et al (2016) proposed a multi-kernel based method to identify the emotion cause from a manually annotated emotion cause corpus. Xu et al (2019) proposed a method based on learning to re-rank candidate emotion cause clauses with extracting a number of emotion-dependent and emotion-independent features. However, these methods are heavily dependent on the expensive human-based features and are too difficult in a real-world application.…”

“…Previous approaches for emotion cause analysis mostly depend on rule-based methods and machine learning algorithms (Ghazi et al, 2015;Gui et al, 2016;Xu et al, 2019). Most of them rely heavily on complicated linguistic rules or feature engineering, which is time-consuming and labor-intensive.…”

A Mutually Auxiliary Multitask Model With Self-Distillation for Emotion-Cause Pair Extraction

“…In addition, inspired by methods on other NLP tasks, researchers have made a lot of new attempts. For example, Ding et al [34] and Xu et al [35] both transformed the ECE task into a clause ordering problem in the perspective of information retrieval. Learning from machine reading comprehension, Diao et al [36] designed a multi-granularity attention network.…”

End-to-End Emotion-Cause Pair Extraction based on Sliding Window Multi-Label Learning

“…(Gui et al, 2016a) released a public corpus and defined the ECE task as a finegrained emotion analysis task, where the goal is to judge for each clause in the document whether it is the corresponding cause, given the annotation of emotions. This corpus has received a lot of attention in subsequent research and has become a benchmark dataset for the ECE task Yu et al, 2019;Xu et al, 2019;. However, there are several inherent shortcomings in the setting of the ECE task: firstly, the need for emotion annotation greatly limits the practical applications of the ECE task; secondly, the way of annotating emotions before extracting causes ignores the fact that emotions and causes are mutually indicative.…”