Related papers: Towards Multimodal Sentiment Analysis Debiasing vi…

Multimodal Sentiment Analysis (MSA) leverages multiple data modals to analyze human sentiment. Existing MSA models generally employ cutting-edge multimodal fusion and representation learning-based methods to promote MSA capability. However,…

Multimodal emotion recognition in conversations (mERC) is an active research topic in natural language processing (NLP), which aims to predict human's emotional states in communications of multiple modalities, e,g., natural language and…

Counterfactuals, serving as one of the emerging type of model interpretations, have recently received attention from both researchers and practitioners. Counterfactual explanations formalize the exploration of ``what-if'' scenarios, and are…

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused…

Meta-analysis is a systematic approach for understanding a phenomenon by analyzing the results of many previously published experimental studies. It is central to deriving conclusions about the summary effect of treatments and interventions…

Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with…

Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings…

Aspect-based-sentiment-analysis (ABSA) is a fine-grained sentiment evaluation task, which analyzes the emotional polarity of the evaluation aspects. Generally, the emotional polarity of an aspect exists in the corresponding opinion…

VQA models may tend to rely on language bias as a shortcut and thus fail to sufficiently learn the multi-modal knowledge from both vision and language. Recent debiasing methods proposed to exclude the language prior during inference.…

Current multimodal sentiment analysis frames sentiment score prediction as a general Machine Learning task. However, what the sentiment score actually represents has often been overlooked. As a measurement of opinions and affective states,…

Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counterfactuals to…

Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and racial bias, giving…

Multimodal Sentiment Analysis (MSA) has been a popular topic in natural language processing nowadays, at both sentence and aspect level. However, the existing approaches almost require large-size labeled datasets, which bring about large…

Multimodal respiratory sound classification offers promise for early pulmonary disease detection by integrating bioacoustic signals with patient metadata. Nevertheless, current approaches remain vulnerable to spurious correlations from…

Aspect-based sentiment analysis (ABSA) garnered growing research interest in multilingual contexts in the past. However, the majority of the studies lack more robust feature alignment and finer aspect-level alignment. In this paper, we…

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…

Aspect-based sentiment analysis (ABSA) aims at analyzing the sentiment of a given aspect in a sentence. Recently, neural network-based methods have achieved promising results in existing ABSA datasets. However, these datasets tend to…

As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models,…

Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, most existing research assume that all modalities are available during both training and testing,…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…