Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hanlei, Xu, Hua, Long, Fei, Wang, Xin, Gao, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929351417659392
author Zhang, Hanlei
Xu, Hua
Long, Fei
Wang, Xin
Gao, Kai
author_facet Zhang, Hanlei
Xu, Hua
Long, Fei
Wang, Xin
Gao, Kai
contents Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex semantics in unsupervised scenarios. This paper introduces a novel unsupervised multimodal clustering method (UMC), making a pioneering contribution to this field. UMC introduces a unique approach to constructing augmentation views for multimodal data, which are then used to perform pre-training to establish well-initialized representations for subsequent clustering. An innovative strategy is proposed to dynamically select high-quality samples as guidance for representation learning, gauged by the density of each sample's nearest neighbors. Besides, it is equipped to automatically determine the optimal value for the top-$K$ parameter in each cluster to refine sample selection. Finally, both high- and low-quality samples are used to learn representations conducive to effective clustering. We build baselines on benchmark multimodal intent and dialogue act datasets. UMC shows remarkable improvements of 2-6\% scores in clustering metrics over state-of-the-art methods, marking the first successful endeavor in this domain. The complete code and data are available at https://github.com/thuiar/UMC.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12775
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances
Zhang, Hanlei
Xu, Hua
Long, Fei
Wang, Xin
Gao, Kai
Multimedia
Artificial Intelligence
Computation and Language
Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex semantics in unsupervised scenarios. This paper introduces a novel unsupervised multimodal clustering method (UMC), making a pioneering contribution to this field. UMC introduces a unique approach to constructing augmentation views for multimodal data, which are then used to perform pre-training to establish well-initialized representations for subsequent clustering. An innovative strategy is proposed to dynamically select high-quality samples as guidance for representation learning, gauged by the density of each sample's nearest neighbors. Besides, it is equipped to automatically determine the optimal value for the top-$K$ parameter in each cluster to refine sample selection. Finally, both high- and low-quality samples are used to learn representations conducive to effective clustering. We build baselines on benchmark multimodal intent and dialogue act datasets. UMC shows remarkable improvements of 2-6\% scores in clustering metrics over state-of-the-art methods, marking the first successful endeavor in this domain. The complete code and data are available at https://github.com/thuiar/UMC.
title Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances
topic Multimedia
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2405.12775