GPF: Generative Prediction Fusion for Multi-Label Emotion Classification

Multi-label Emotion Classification (MEC) is a fundamental and challenging task in natural language processing. The MEC task aims to recognize at least an emotion from a sentence. Previous seq2seq based models required to transform the set of labels into a sequence. However, the labels in the sentenc...

Full description

Saved in:
Bibliographic Details
Main Authors: Huang, Shiqiao, Zhang, Weiwen, Lin, Nankai, Xu, Mianshen
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Contrastive learning
Decoding
Emotion recognition
Federated learning
Fusion Strategy
Multi-label Emotion Classification
Natural language processing
Non-Autoregressive Decoder
Transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multi-label Emotion Classification (MEC) is a fundamental and challenging task in natural language processing. The MEC task aims to recognize at least an emotion from a sentence. Previous seq2seq based models required to transform the set of labels into a sequence. However, the labels in the sentence are unordered. In this paper, we propose GPF as a framework of generative prediction fusion for MEC. Specifically, we utilize the non-autoregressive decoder to simultaneously generate the set of labels and propose an output fusion strategy for MEC. Meanwhile, we develop a multi-label contrastive learning to enhance the representation of our model. Experiment results on three distinct language datasets demonstrate the effectiveness of our model.
ISSN:2768-1904
DOI:10.1109/CSCWD61410.2024.10580482