Saved in:
Bibliographic Details
Main Authors: Liu, Yingjian, Li, Jiang, Wang, Xiaoping, Zeng, Zhigang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.11117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913273947881472
author Liu, Yingjian
Li, Jiang
Wang, Xiaoping
Zeng, Zhigang
author_facet Liu, Yingjian
Li, Jiang
Wang, Xiaoping
Zeng, Zhigang
contents Emotion Recognition in Conversation (ERC) has attracted growing attention in recent years as a result of the advancement and implementation of human-computer interface technologies. In this paper, we propose an emotional inertia and contagion-driven dependency modeling approach (EmotionIC) for ERC task. Our EmotionIC consists of three main components, i.e., Identity Masked Multi-Head Attention (IMMHA), Dialogue-based Gated Recurrent Unit (DiaGRU), and Skip-chain Conditional Random Field (SkipCRF). Compared to previous ERC models, EmotionIC can model a conversation more thoroughly at both the feature-extraction and classification levels. The proposed model attempts to integrate the advantages of attention- and recurrence-based methods at the feature-extraction level. Specifically, IMMHA is applied to capture identity-based global contextual dependencies, while DiaGRU is utilized to extract speaker- and temporal-aware local contextual information. At the classification level, SkipCRF can explicitly mine complex emotional flows from higher-order neighboring utterances in the conversation. Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark datasets. The ablation studies confirm that our modules can effectively model emotional inertia and contagion.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11117
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation
Liu, Yingjian
Li, Jiang
Wang, Xiaoping
Zeng, Zhigang
Computation and Language
Emotion Recognition in Conversation (ERC) has attracted growing attention in recent years as a result of the advancement and implementation of human-computer interface technologies. In this paper, we propose an emotional inertia and contagion-driven dependency modeling approach (EmotionIC) for ERC task. Our EmotionIC consists of three main components, i.e., Identity Masked Multi-Head Attention (IMMHA), Dialogue-based Gated Recurrent Unit (DiaGRU), and Skip-chain Conditional Random Field (SkipCRF). Compared to previous ERC models, EmotionIC can model a conversation more thoroughly at both the feature-extraction and classification levels. The proposed model attempts to integrate the advantages of attention- and recurrence-based methods at the feature-extraction level. Specifically, IMMHA is applied to capture identity-based global contextual dependencies, while DiaGRU is utilized to extract speaker- and temporal-aware local contextual information. At the classification level, SkipCRF can explicitly mine complex emotional flows from higher-order neighboring utterances in the conversation. Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark datasets. The ablation studies confirm that our modules can effectively model emotional inertia and contagion.
title EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation
topic Computation and Language
url https://arxiv.org/abs/2303.11117