End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network

Published in

International Conference on Computational Lingu...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

A novel end-to-end Pair Graph Convolutional Network (PairGCN) is presented to model pair-level contexts so that to capture the dependency information among local neighborhood candidate pairs.

Abstract

Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages. Considering that most emotions usually have few causes mentioned in their contexts, we present a novel end-to-end Pair Graph Convolutional Network (PairGCN) to model pair-level contexts so that to capture the dependency information among local neighborhood candidate pairs. Moreover, in the graphical network, contexts are grouped into three types and each type of contexts is propagated by its own way. Experiments on a benchmark Chinese emotion-cause pair extraction corpus demonstrate the effectiveness of the proposed model.

Authors

Ying Chen

1 papers

Wenjun Hou

1 papers

Shoushan Li

1 papers

References24 items

Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree

DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation

Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

Graph Convolutional Networks for Text Classification

End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network

Published in

International Conference on Computational Lingu...(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

A novel end-to-end Pair Graph Convolutional Network (PairGCN) is presented to model pair-level contexts so that to capture the dependency information among local neighborhood candidate pairs.

Abstract

Authors

Ying Chen

1 papers

Wenjun Hou

1 papers

Shoushan Li

1 papers

References24 items

Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree

DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation

Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

Graph Convolutional Networks for Text Classification

Xiaoqiang Zhang

1 papers

A Bootstrap Method for Automatic Rule Acquisition on Emotion Cause Extraction

A Question Answering Approach for Emotion Cause Extraction

Event-Driven Emotion Cause Extraction with Corpus Construction

Semi-Supervised Classification with Graph Convolutional Networks

A rule-based approach to emotion cause detection for Chinese micro-blogs

Emotion Cause Detection for Chinese Micro-Blogs Based on ECOCC Model

Adam: A Method for Stochastic Optimization

Text-based emotion classification using emotion cause extraction

Distributed Representations of Words and Phrases and their Compositionality

Extracting Causes of Emotions from Text

Emotion Cause Detection with Linguistic Constructions

Rectified Linear Units Improve Restricted Boltzmann Machines

A Text-driven Rule-based System for Emotion Cause Detection

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Multiple Level Hierarchical Network-Based Clause Selection for Emotion Cause Extraction

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

Joint Learning for Emotion Classification and Emotion Cause Detection

A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness

Dropout: a simple way to prevent neural networks from overfitting

Field of Study

Computer Science

Venue Information

Name

International Conference on Computational Linguistics

Type

conference

URL

https://www.aclweb.org/anthology/venues/coling/

Alternate Names

Int Conf Comput Linguistics
COLING