Гендерный уклон

AbstractLanguage is increasingly being used to de-fine rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage …...

Like many social variables, gender pervasively influences how people communicate with one another. However, prior computational work has largely focused on linguistic gender difference and communications about gender, rather than …...

AbstractWe present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of English …...

AbstractRecent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in …...

AbstractThis paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is …...

AbstractWord embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon …...

AbstractAs Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although …...

AbstractThere is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, …...

AbstractIn automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech …...

AbstractWord embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply …...

AbstractMultilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have …...

AbstractGender bias in machine translation can manifest when choosing gender inflections based on spurious gender correlations. For example, always translating doctors as men and nurses as women. This can be …...

AbstractTranslating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data …...

AbstractAttention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly …...

AbstractPretrained language models (PLMs) learn stereotypes held by humans and reflected in text from their training corpora, including gender bias. When PLMs are used for downstream tasks such as picking …...

AbstractMachine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a …...

AbstractSocial biases present in data are often directly reflected in the predictions of models trained on that data. We analyze gender bias in dialogue data, and examine how this bias …...

AbstractTraining 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 …...

AbstractCorrectly resolving textual mentions of people fundamentally entails making inferences about those people. Such inferences raise the risk of systemic biases in coreference resolution systems, including biases that can harm …...

AbstractRecent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction. While much attention has been dedicated towards improvements in accuracy, there have been no …...

AbstractThe one-sided focus on English in previous studies of gender bias in NLP misses out on opportunities in other languages: English challenge datasets such as GAP and WinoGender highlight model …...

AbstractDespite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias …...

AbstractVolatility prediction is complex due to the stock market’s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and …...

AbstractVarious measures have been proposed to quantify human-like social biases in word embeddings. However, bias scores based on these measures can suffer from measurement error. One indication of measurement quality …...

Reporting and providing test sets for harm- ful bias in NLP applications is essential for building a robust understanding of the cur- rent problem. We present a new observation of …...

AbstractHuman-like biases and undesired social stereotypes exist in large pretrained language models. Given the wide adoption of these models in real-world applications, mitigating such biases has become an emerging and …...

. This paper describes a study on gender bias in French/English neural machine trans- lation (MT) systems. We introduce a controlled corpus to measure the intensity of such biases in …...

AbstractWith the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done …...

AbstractThe scientific community is increasingly aware of the necessity to embrace pluralism and consistently represent major and minor social groups. Currently, there are no standard evaluation techniques for different types …...

AbstractGenerating machine translations via beam search seeks the most likely output under a model. However, beam search has been shown to amplify demographic biases exhibited by a model. We aim …...

AbstractWarning: This paper contains explicit statements of offensive stereotypes which may be upsetting. Much work on biases in natural language processing has addressed biases linked to the social and cultural …...

AbstractMasked Language Models (MLMs) pre-trained by predicting masked tokens on large corpora have been used successfully in natural language processing tasks for a variety of languages. Unfortunately, it was reported …...

AbstractMovies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always …...

AbstractCommon studies of gender bias in NLP focus either on extrinsic bias measured by model performance on a downstream task or on intrinsic bias found in models’ internal representations. However, …...

AbstractText-to-image generative models have achieved unprecedented success in generating high-quality images based on natural language descriptions. However, it is shown that these models tend to favor specific social groups when …...

AbstractStudying and mitigating gender and other biases in natural language have become important areas of research from both algorithmic and data perspectives. This paper explores the idea of reducing gender …...

AbstractGender bias in natural language processing (NLP) applications, particularly machine translation, has been receiving increasing attention. Much of the research on this issue has focused on mitigating gender bias in …...

To assess whether neural language models cap- ture discourse-level linguistic knowledge, pre- vious work has tested whether they exhibit the well-known implicit causality (IC) bias found in various interpersonal verbs …...

AbstractWomen are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natural …...

AbstractGender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages. However, most of current evaluation practices adopt …...

AbstractKnowledge base (KB) embeddings have been shown to contain gender biases. In this paper, we study two questions regarding these biases: how to quantify them, and how to trace their …...

AbstractSocial biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing …...

AbstractModels trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., …...

AbstractredWarning: This paper contains content that may be offensive or upsetting.Pretrained conversational agents have been exposed to safety issues, exhibiting a range of stereotypical human biases such as gender bias. …...

AbstractMachine Translation (MT) models are well-known to suffer from gender bias, especially for gender beyond a binary conception. Due to the multiplicity of language-specific strategies for gender representation beyond the …...

AbstractPredictions from machine learning models can reflect bias in the data on which they are trained. Gender bias has been shown to be prevalent in natural language processing models. The …...

AbstractContent Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly …...

AbstractLink prediction models based on factual knowledge graphs are commonly used in applications such as search and question answering. However, work investigating social bias in these models has been limited. …...