Related papers: Cross-Platform and Cross-Domain Abusive Language D…
Abusive language is a concerning problem in online social media. Past research on detecting abusive language covers different platforms, languages, demographies, etc. However, models trained using these datasets do not perform well in…
Contrastive learning has demonstrated promising performance in image and text domains either in a self-supervised or a supervised manner. In this work, we extend the supervised contrastive learning framework to clinical risk prediction…
Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…
A key challenge for Emotion Recognition in Conversations (ERC) is to distinguish semantically similar emotions. Some works utilise Supervised Contrastive Learning (SCL) which uses categorical emotion labels as supervision signals and…
The detection of automated accounts, also known as "social bots", has been an increasingly important concern for online social networks (OSNs). While several methods have been proposed for detecting social bots, significant research gaps…
Large language models (LLMs) are increasingly being used for generating text in a variety of use cases, including journalistic news articles. Given the potential malicious nature in which these LLMs can be used to generate disinformation at…
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorporating SSL. The intuition is to enforce instance-level…
Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…
Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like…
This work focuses on sign language retrieval-a recently proposed task for sign language understanding. Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) retrieval and sign-video-to-text (V2T) retrieval. Different…
The wide adoption of Large language models (LLMs) makes their dependability a pressing concern. Detection of errors is the first step to mitigating their impact on a system and thus, efficient error detection for LLMs is an important issue.…
Massive rumors usually appear along with breaking news or trending topics, seriously hindering the truth. Existing rumor detection methods are mostly focused on the same domain, and thus have poor performance in cross-domain scenarios due…
To overcome the data-hungry challenge, we have proposed a semi-supervised contrastive learning framework for the task of class-imbalanced semantic segmentation. First and foremost, to make the model operate in a semi-supervised manner, we…
Cross-lingual Named Entity Recognition (NER) has recently become a research hotspot because it can alleviate the data-hungry problem for low-resource languages. However, few researches have focused on the scenario where the source-language…
Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored,…
This paper tries to address the problem of abusive comment detection in low-resource indic languages. Abusive comments are statements that are offensive to a person or a group of people. These comments are targeted toward individuals…
Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer…
We experiment graph-based Semi-Supervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt…
With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these models. While supervised AI-generated text detectors perform…
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…