Related papers: NeuTral Rewriter: A Rule-Based and Neural Approach…

A significant portion of the textual data used in the field of Natural Language Processing (NLP) exhibits gender biases, particularly due to the use of masculine generics (masculine words that are supposed to refer to mixed groups of men…

Gender-neutral rewriting (GNR) aims to reformulate text to eliminate unnecessary gender specifications while preserving meaning, a particularly challenging task in grammatical-gender languages like Italian. In this work, we conduct the…

Responsible development of technology involves applications being inclusive of the diverse set of users they hope to support. An important part of this is understanding the many ways to refer to a person and being able to fluently change…

Gender bias is a frequent occurrence in NLP-based applications, especially pronounced in gender-inflected languages. Bias can appear through associations of certain adjectives and animate nouns with the natural gender of referents, but also…

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…

In this paper, we define the task of gender rewriting in contexts involving two users (I and/or You) - first and second grammatical persons with independent grammatical gender preferences. We focus on Arabic, a gender-marking…

Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes…

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

Gender-neutral translation (GNT) that avoids biased and undue binary assumptions is a pivotal challenge for the creation of more inclusive translation technologies. Advancements for this task in Machine Translation (MT), however, are…

Texts like news, encyclopedias, and some social media strive for objectivity. Yet bias in the form of inappropriate subjectivity - introducing attitudes via framing, presupposing truth, and casting doubt - remains ubiquitous. This kind of…

Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment. Existing methods to mitigate bias lack a comprehensive understanding of its mechanisms or compromise the model's core capabilities. To…

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,…

Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce translation quality, particularly when the target language…

Recent advances in neural methods have led to substantial improvement in the quality of Neural Machine Translation (NMT) systems. However, these systems frequently produce translations with inaccurate gender (Stanovsky et al., 2019), which…

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

We introduce NeuSpell, an open-source toolkit for spelling correction in English. Our toolkit comprises ten different models, and benchmarks them on naturally occurring misspellings from multiple sources. We find that many systems do not…

Neural Machine Translation (NMT) models, though state-of-the-art for translation, often reflect social biases, particularly gender bias. Existing evaluation benchmarks primarily focus on English as the source language of translation. For…

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…

Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek to control gender…

Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high precision, they do not flexibly handle errors such as…