Emotion-Cause Pair Extraction as Question Answering

TL;DR

This paper reformulates the Emotion-Cause Pair Extraction task as a question answering problem, introducing a simple BERT-based model that predicts emotion and cause pairs effectively, simplifying previous complex methods.

Contribution

The paper presents a novel QA-based approach for ECPE, demonstrating that a straightforward BERT model can outperform complex architectures in extracting emotion-cause pairs.

Findings

The Guided-QA model achieves promising results on standard ECPE datasets.

The approach simplifies ECPE modeling by framing it as a QA task.

The method is easy to reproduce and effective despite its simplicity.

Abstract

The task of Emotion-Cause Pair Extraction (ECPE) aims to extract all potential emotion-cause pairs of a document without any annotation of emotion or cause clauses. Previous approaches on ECPE have tried to improve conventional two-step processing schemes by using complex architectures for modeling emotion-cause interaction. In this paper, we cast the ECPE task to the question answering (QA) problem and propose simple yet effective BERT-based solutions to tackle it. Given a document, our Guided-QA model first predicts the best emotion clause using a fixed question. Then the predicted emotion is used as a question to predict the most potential cause for the emotion. We evaluate our model on a standard ECPE corpus. The experimental results show that despite its simplicity, our Guided-QA achieves promising results and is easy to reproduce. The code of Guided-QA is also provided.