相关论文: Human-Guided Fair Classification for Natural Langu…

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide important features which…

The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this…

Recent work in fair machine learning has proposed dozens of technical definitions of algorithmic fairness and methods for enforcing these definitions. However, we still lack an understanding of how to develop machine learning systems with…

With the surge in user-generated textual information, there has been a recent increase in the use of summarization algorithms for providing an overview of the extensive content. Traditional metrics for evaluation of these algorithms (e.g.…

In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual…

Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate affective (emotional) text. We posit a model…

Fair machine learning aims to mitigate the biases of model predictions against certain subpopulations regarding sensitive attributes such as race and gender. Among the many existing fairness notions, counterfactual fairness measures the…

Text classification is the automated assignment of natural language texts to predefined categories based on their content. Text classification is the primary requirement of text retrieval systems, which retrieve texts in response to a user…

With the rise of advanced natural language models like GPT, distinguishing between human-written and GPT-generated text has become increasingly challenging and crucial across various domains, including academia. The long-standing issue of…

This work examines how to train fair classifiers in settings where training labels are corrupted with random noise, and where the error rates of corruption depend both on the label class and on the membership function for a protected…

Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases) is hardly possible, many real-world text classifiers are trained on the available, yet imperfect,…

ChatGPT has garnered significant interest due to its impressive performance; however, there is growing concern about its potential risks, particularly in the detection of AI-generated content (AIGC), which is often challenging for untrained…

We present a supervised learning algorithm for text categorization which has brought the team of authors the 2nd place in the text categorization division of the 2012 Cybersecurity Data Mining Competition (CDMC'2012) and a 3rd prize…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

The advancing fluency of LLMs raises important questions about their ability to emulate complex human traits, including emotional expression and personality, across diverse linguistic and cultural contexts. This study investigates whether…

Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…

Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between…

The fairness in machine learning is getting increasing attention, as its applications in different fields continue to expand and diversify. To mitigate the discriminated model behaviors between different demographic groups, we introduce a…

In recent years, there has been an exponential growth in the number of complex documents and texts that require a deeper understanding of machine learning methods to be able to accurately classify texts in many applications. Many machine…

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen…