speech-8

Emotion Cause Extraction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in emotion-cause-extraction-25

Trend

Dataset

Best Model

Actions

ECE

Libraries

i

Use these libraries to find emotion-cause-extraction-25 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

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

Rui Xia, Zixiang Ding•Mon Jun 03 2019

A 2-step approach is proposed to address this new ECPE task, which first performs individual emotion extraction and cause extraction via multi-task learning, and then conduct emotion-cause pairing and filtering.

234

Content

0

Paper Graph

End-to-end Emotion-Cause Pair Extraction via Learning to Link

Haolin Song, Chen Zhang, Qiuchi Li, D. Song•Mon Feb 24 2020

This work proposes a multi-task learning model that can extract emotions, causes and emotion-cause pairs simultaneously in an end-to-end manner and outperforms a range of state-of-the-art approaches in terms of both effectiveness and efficiency.

27 0

Paper Graph

RTHN: A RNN-Transformer Hierarchical Network for Emotion Cause Extraction

Rui Xia, Zixiang Ding, Mengran Zhang•Mon Jun 03 2019

A joint emotion cause extraction framework, named RNN-Transformer Hierarchical Network (RTHN), to encode and classify multiple clauses synchronously and achieve the best performance among 12 compared systems.

107 0

Paper Graph

From Independent Prediction to Re-ordered Prediction: Integrating Relative Position and Global Label Information to Emotion Cause Identification

Rui Xia, Zixiang Ding, Mengran Zhang, Huihui He•Mon Jun 03 2019

This work proposes a model based on the neural network architecture to encode the three elements of emotion cause identification, in an unified and end-to-end fashion, and introduces a relative position augmented embedding learning algorithm and a reordered prediction mechanism with dynamic global labels.

87 0

Paper Graph

An Experimental Study of The Effects of Position Bias on Emotion CauseExtraction

Jiayuan Ding, M. Kejriwal•Wed Jul 15 2020

A simple random selection approach toward ECE that does not require observing the text achieves similar performance compared to the baselines, and concludes that it is the innate bias in this benchmark that caused high accuracy rate of these deep learning models in ECE.

11 0

Paper Graph

Recognizing Emotion Cause in Conversations

Devamanyu Hazarika, Soujanya Poria, Rishabh Bhardwaj, Navonil Majumder, A. Gelbukh, Deepanway Ghosal, Samson Yu, Pengfei Hong, Romila Ghosh, Niyati Chhaya, Rada Mihalcea•Mon Dec 21 2020

This work introduces a new task highly relevant for (explainable) emotion-aware artificial intelligence: recognizing emotion cause in conversations, provides a new highly challenging publicly available dialogue-level dataset for this task, and gives strong baseline results on this dataset.

151 0

Paper Graph

An End-to-End Network for Emotion-Cause Pair Extraction

Ashutosh Modi, Shreeshail Hingane, Saim Wani•Mon Mar 01 2021

This paper adapts the NTCIR-13 ECE corpus and establishes a baseline for the ECPE task to produce significant performance improvements over the multi-stage approach and achieves comparable performance to the state-of-the-art methods.

46 0

Paper Graph

A Dual-Questioning Attention Network for Emotion-Cause Pair Extraction with Context Awareness

Qixuan Sun, Yaqi Yin, Hong Yu•Wed Apr 14 2021

A Dual-Questioning Attention Network is proposed to alleviate limitations in emotion cause extraction by question candidate emotions and causes to the context independently through attention networks for a contextual and semantical answer.

14 0

Paper Graph

Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction

Lin Gui, Gabriele Pergola, Yulan He, Hanqi Yan•Sun Jun 06 2021

A novel graph-based method is proposed to explicitly model the emotion triggering paths by leveraging the commonsense knowledge to enhance the semantic dependencies between a candidate clause and an emotion clause and is more robust against adversarial attacks compared to existing models.

52 0

Paper Graph

Adding a benchmark result helps the community track progress.