Related papers: Emotions are Subtle: Learning Sentiment Based Text…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical success, theoretical understanding of the superiority of…

Human emotion is expressed in many communication modalities and media formats and so their computational study is equally diversified into natural language processing, audio signal analysis, computer vision, etc. Similarly, the large…

We analyze the process of creating word embedding feature representations designed for a learning task when annotated data is scarce, for example, in depressive language detection from Tweets. We start with a rich word embedding pre-trained…

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within…

Targeted Sentiment Analysis aims to extract sentiment towards a particular target from a given text. It is a field that is attracting attention due to the increasing accessibility of the Internet, which leads people to generate an enormous…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous…

Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner. It has in general two sub-tasks: (i) extracting aspects from each review, and (ii) classifying aspect-based reviews…

Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop systems to predict political elections, measure economic…

Scientific articles are long text documents organized into sections, each describing aspects of the research. Analyzing scientific production has become progressively challenging due to the increase in the number of available articles.…

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…

Natural Language Processing models like BERT can provide state-of-the-art word embeddings for downstream NLP tasks. However, these models yet to perform well on Semantic Textual Similarity, and may be too large to be deployed as lightweight…

The emerging technique of deep learning has been widely applied in many different areas. However, when adopted in a certain specific domain, this technique should be combined with domain knowledge to improve efficiency and accuracy. In…

Undoubtedly that the Bidirectional Encoder representations from Transformers is the most powerful technique in making Natural Language Processing tasks such as Named Entity Recognition, Question & Answers or Sentiment Analysis, however, the…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…