Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lin, Jinhao, Wang, Yifei, Xu, Yanwu, Liu, Qi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.09784
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910743546298368
author Lin, Jinhao
Wang, Yifei
Xu, Yanwu
Liu, Qi
author_facet Lin, Jinhao
Wang, Yifei
Xu, Yanwu
Liu, Qi
contents Despite multimodal sentiment analysis being a fertile research ground that merits further investigation, current approaches take up high annotation cost and suffer from label ambiguity, non-amicable to high-quality labeled data acquisition. Furthermore, choosing the right interactions is essential because the significance of intra- or inter-modal interactions can differ among various samples. To this end, we propose Semi-IIN, a Semi-supervised Intra-inter modal Interaction learning Network for multimodal sentiment analysis. Semi-IIN integrates masked attention and gating mechanisms, enabling effective dynamic selection after independently capturing intra- and inter-modal interactive information. Combined with the self-training approach, Semi-IIN fully utilizes the knowledge learned from unlabeled data. Experimental results on two public datasets, MOSI and MOSEI, demonstrate the effectiveness of Semi-IIN, establishing a new state-of-the-art on several metrics. Code is available at https://github.com/flow-ljh/Semi-IIN.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09784
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semi-IIN: Semi-supervised Intra-inter modal Interaction Learning Network for Multimodal Sentiment Analysis
Lin, Jinhao
Wang, Yifei
Xu, Yanwu
Liu, Qi
Computation and Language
Artificial Intelligence
Despite multimodal sentiment analysis being a fertile research ground that merits further investigation, current approaches take up high annotation cost and suffer from label ambiguity, non-amicable to high-quality labeled data acquisition. Furthermore, choosing the right interactions is essential because the significance of intra- or inter-modal interactions can differ among various samples. To this end, we propose Semi-IIN, a Semi-supervised Intra-inter modal Interaction learning Network for multimodal sentiment analysis. Semi-IIN integrates masked attention and gating mechanisms, enabling effective dynamic selection after independently capturing intra- and inter-modal interactive information. Combined with the self-training approach, Semi-IIN fully utilizes the knowledge learned from unlabeled data. Experimental results on two public datasets, MOSI and MOSEI, demonstrate the effectiveness of Semi-IIN, establishing a new state-of-the-art on several metrics. Code is available at https://github.com/flow-ljh/Semi-IIN.
title Semi-IIN: Semi-supervised Intra-inter modal Interaction Learning Network for Multimodal Sentiment Analysis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.09784