Chrome Extension
WeChat Mini Program
Use on ChatGLM

ConFEDE: Contrastive Feature Decomposition for Multimodal Sentiment Analysis.

Annual Meeting of the Association for Computational Linguistics (ACL)(2023)CCF A

Univ Alberta | Tencent

Cited 43|Views276
Abstract
Multimodal Sentiment Analysis aims to predict the sentiment of video content. Recent research suggests that multimodal sentiment analysis critically depends on learning a good representation of multimodal information, which should contain both modality-invariant representations that are consistent across modalities as well as modality-specific representations. In this paper, we propose ConFEDE, a unified learning framework that jointly performs contrastive representation learning and contrastive feature decomposition to enhance representation of multimodal information. It decomposes each of the three modalities of a video sample, including text, video frames, and audio, into a similarity feature and a dissimilarity feature, which are learned by a contrastive relation centered around text. We conducted extensive experiments on CH-SIMS, MOSI and MOSEI to evaluate various state-of-the-art multimodal sentiment analysis methods. Experimental results show that ConFEDE outperforms all baselines on these datasets on a range of metrics.
More
Translated text
Key words
Emotion Recognition,Aspect-based Sentiment Analysis,Feature Extraction,Sentiment Analysis
PDF
Bibtex
AI Read Science
Video&Figures
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers
Neusoft Medical Systems Ltd.,Chen Lei,Li Xiangju, Lv Xiaofeng,Xia Shuyue, Shenzhen Technology University
2020

被引用626 | 浏览

Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了ConFEDE,一种统一的学习框架,通过联合进行对比表征学习和对比特征分解来增强多模态信息的表征,提高了多模态情感分析的准确性。

方法】:ConFEDE框架将视频样本的文本、视频帧和音频三种模态分别分解为相似性特征和差异性特征,通过以文本为中心的对比关系进行学习。

实验】:在CH-SIMS、MOSI和MOSEI数据集上进行了广泛的实验,对比了多种最先进的多模态情感分析方法,结果显示ConFEDE在多个指标上均优于所有基线方法。