相关论文: Disentangling Dialect from Social Bias via Multita…

This paper studies the performance of large language models (LLMs), particularly regarding demographic fairness, in solving real-world healthcare tasks. We evaluate state-of-the-art LLMs with three prevalent learning frameworks across six…

Media has a substantial impact on the public perception of events. A one-sided or polarizing perspective on any topic is usually described as media bias. One of the ways how bias in news articles can be introduced is by altering word…

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple…

Instruction-guided text-to-speech (TTS) research has reached a maturity level where excellent speech generation quality is possible on demand, yet two coupled biases persist in reducing perceived quality: accent bias, where models default…

Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks. It has shown great success in natural language processing (NLP). Currently, a…

Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized…

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation…

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…

Privacy policies inform users about data collection and usage, yet their complexity limits accessibility for diverse populations. Existing Privacy Policy Question Answering (QA) systems exhibit performance disparities across English…

Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mitigate these biases…

This paper is a summary of the work done in my PhD thesis. Where I investigate the impact of bias in NLP models on the task of hate speech detection from three perspectives: explainability, offensive stereotyping bias, and fairness. Then, I…

Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models often focus on extracting shared information across…

As natural language processing systems become more widespread, it is necessary to address fairness issues in their implementation and deployment to ensure that their negative impacts on society are understood and minimized. However, there…

In Natural Language Processing (NLP), variation is typically seen as noise and "normalised away" before processing, even though it is an integral part of language. Conversely, studying language variation in social contexts is central to…

This study focuses on recognizing Bangladeshi dialects and converting diverse Bengali accents into standardized formal Bengali speech. Dialects, often referred to as regional languages, are distinctive variations of a language spoken in a…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous studies use…

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language. Our starting point is a…