相关论文: What Triggers my Model? Contrastive Explanations I…

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this,…

Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on…

Gender-neutral translation (GNT) aims to avoid expressing the gender of human referents when the source text lacks explicit cues about the gender of those referents. Evaluating GNT automatically is particularly challenging, with current…

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification…

Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…

Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns. For example, in speech translation (ST), when translating from languages with…

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…

Implicit gender bias in Large Language Models (LLMs) is a well-documented problem, and implications of gender introduced into automatic translations can perpetuate real-world biases. However, some LLMs use heuristics or post-processing to…

Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers…

While machine translation (MT) systems have seen significant improvements, it is still common for translations to reflect societal biases, such as gender bias. Decoder-only Large Language Models (LLMs) have demonstrated potential in MT,…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance…

Gender-inclusive machine translation (MT) should preserve gender ambiguity in the source to avoid misgendering and representational harms. While gender ambiguity often occurs naturally in notional gender languages such as English,…

The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory…

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which…

The vast majority of work on gender in MT focuses on 'unambiguous' inputs, where gender markers in the source language are expected to be resolved in the output. Conversely, this paper explores the widespread case where the source sentence…

Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by…

Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in…

The rapid advancement of Large Language Models (LLMs) has sparked intense debate regarding the prevalence of bias in these models and its mitigation. Yet, as exemplified by both results on debiasing methods in the literature and reports of…