DeepAI AI Chat
Log In Sign Up

Multi-Task Learning Framework for Extracting Emotion Cause Span and Entailment in Conversations

by   Ashwani Bhat, et al.
Indian Institute of Technology Kanpur

Predicting emotions expressed in text is a well-studied problem in the NLP community. Recently there has been active research in extracting the cause of an emotion expressed in text. Most of the previous work has done causal emotion entailment in documents. In this work, we propose neural models to extract emotion cause span and entailment in conversations. For learning such models, we use RECCON dataset, which is annotated with cause spans at the utterance level. In particular, we propose MuTEC, an end-to-end Multi-Task learning framework for extracting emotions, emotion cause, and entailment in conversations. This is in contrast to existing baseline models that use ground truth emotions to extract the cause. MuTEC performs better than the baselines for most of the data folds provided in the dataset.


page 17

page 18


Recognizing Emotion Cause in Conversations

Recognizing the cause behind emotions in text is a fundamental yet under...

Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction

Detecting what emotions are expressed in text is a well-studied problem ...

Multimodal Emotion-Cause Pair Extraction in Conversations

Emotion cause analysis has received considerable attention in recent yea...

PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship

Personality and emotion are both central to affective computing. Existin...

Empathic Conversations: A Multi-level Dataset of Contextualized Conversations

Empathy is a cognitive and emotional reaction to an observed situation o...