Today's text classifiers inevitably suffer from unintended dataset biases, especially the
document-level label bias and word-level keyword bias, which may hurt models' …

Recent literature focuses on utilizing the entity information in the sentence-level relation
extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result …

Multi-modal sarcasm detection (MSD), which aims to identify whether a given sample with
multimodal information (ie, text and image) is sarcastic, has garnered widespread attention …

Unintended dataset biases typically exist in existing Emotion Recognition in Conversations
(ERC) datasets, including label bias, where models favor the majority class due to …

The bias of disease prediction in Large Language Models (LLMs) is a critical yet
underexplored issue, with potential implications for healthcare outcomes and equity. As …

In this article, we present a generic inference hybrid structure for Convolutional Recurrent
Neural Network (conv-RNN) text semantic modelling, combining the strengths of …