相关论文: Target-oriented Multimodal Sentiment Classificatio…

Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data. Previous research works rarely consider token-level feature fusion, and few works explore learning the common features…

This paper proposes a novel approach for constructing effective personalized policies when the observed data lacks counter-factual information, is biased and possesses many features. The approach is applicable in a wide variety of settings…

Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing methods still fail to ensure evidence-answer consistency, where correct answers must be…

While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of…

Multimodal sentiment analysis has attracted increasing attention with broad application prospects. The existing methods focuses on single modality, which fails to capture the social media content for multiple modalities. Moreover, in…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

This study addresses generating counterfactual explanations with multimodal information. Our goal is not only to classify a video into a specific category, but also to provide explanations on why it is not categorized to a specific class…

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their…

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language…

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…

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of…

Multimodal speech emotion recognition aims to detect speakers' emotions from audio and text. Prior works mainly focus on exploiting advanced networks to model and fuse different modality information to facilitate performance, while…

The natural language processing and multimedia field has seen a notable surge in interest in multimodal sentiment recognition. Hence, this study aims to employ Target-Dependent Multimodal Sentiment Analysis (TDMSA) to identify the level of…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of…

Background: When neural network emotion and sentiment classifiers are used in public health informatics studies, biases present in the classifiers could produce inadvertently misleading results. Objective: This study assesses the impact of…

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion words, but still convey clear human-aware sentiment…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…