Learn

About this website Definition & extra Information Research on bias

Further academic papers

Piergentili et al. (2023): Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus
Abstract Gender inequality is embedded in our communication practices and perpetuated in translation technologies. This becomes particularly apparent when translating into grammatical gender languages, where machine translation (MT) often defaults to masculine and stereotypical representations by making undue binary gender assumptions. Our work addresses the rising demand for inclusive language by focusing head-on on gender-neutral translation from English to Italian. We start from the essentials: proposing a dedicated benchmark and exploring automated evaluation methods. First, we introduce GeNTE, a natural, bilingual test set for gender-neutral translation, whose creation was informed by a survey on the perception and use of neutral language. Based on GeNTE, we then overview existing reference-based evaluation approaches, highlight their limits, and propose a reference-free method more suitable to assess gender-neutral translation.
Click here to access the article.

Lardelli and Gromann (2023): Gender-Fair (Machine) Translation
Abstract Recent years have seen an increased visibility of non-binary people in public discourse. Accordingly, gender-fair language strategies that go beyond a binary conception of gender have been proposed. Such strategies pose a challenge for both translators and machine translation (MT), and gender-fair (machine) translation represents a relatively novel research field. With this survey and discussion, we hope to provide a starting point for this field and contribute a detailed overview of (machine) translation strategies to counteract the misrepresentation of an individual’s gender. The results show that gender-fair translation studies (TS) approaches largely focus on media translation, such as subtitles or news articles, and the MT results show that the need to include non-binary debiasing methods is increasingly acknowledged, however, hardly ever implemented. Ideas on a closer mutually beneficial interaction between MT and translation studies are presented to advance multilingual gender-fair language use.
Click here to access the article.

Pikuliak et al. (2023): Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling
Abstract We present GEST – a new dataset for measuring gender-stereotypical reasoning in masked LMs and English-to-X machine translation systems. GEST contains samples that are compatible with 9 Slavic languages and English for 16 gender stereotypes about men and women (e.g., Women are beautiful, Men are leaders). The definition of said stereotypes was informed by gender experts. We used GEST to evaluate 11 masked LMs and 4 machine translation systems. We discovered significant and consistent amounts of stereotypical reasoning in almost all the evaluated models and languages.
Click here to access the article.

Devinney et al. (2022): Theories of “Gender” in NLP Bias Research
Abstract The rise of concern around Natural Language Processing (NLP) technologies containing and perpetuating social biases has led to a rich and rapidly growing area of research. Gender bias is one of the central biases being analyzed, but to date there is no comprehensive analysis of how “gender” is theorized in the field. We survey nearly 200 articles concerning gender bias in NLP to discover how the field conceptualizes gender both explicitly (e.g. through definitions of terms) and implicitly (e.g. through how gender is operationalized in practice). In order to get a better idea of emerging trajectories of thought, we split these articles into two sections by time. We find that the majority of the articles do not make their theorization of gender explicit, even if they clearly define “bias.” Almost none use a model of gender that is intersectional or inclusive of nonbinary genders; and many conflate sex characteristics, social gender, and linguistic gender in ways that disregard the existence and experience of trans, nonbinary, and intersex people. There is an increase between the two time-sections in statements acknowledging that gender is a complicated reality, however, very few articles manage to put this acknowledgment into practice. In addition to analyzing these findings, we provide specific recommendations to facilitate interdisciplinary work, and to incorporate theory and methodology from Gender Studies. Our hope is that this will produce more inclusive gender bias research in NLP.
Click here to access the article.

Costa-jussà et al. (2022): Interpreting Gender Bias in Neural Machine Translation: Multilingual Architecture Matters
Abstract Multilingual neural machine translation architectures mainly differ in the number of sharing modules and parameters applied among languages. In this paper, and from an algorithmic perspective, we explore whether the chosen architecture, when trained with the same data, influences the level of gender bias. Experiments conducted in three language pairs show that language-specific encoder-decoders exhibit less bias than the shared architecture. We propose two methods for interpreting and studying gender bias in machine translation based on source embeddings and attention. Our analysis shows that, in the language-specific case, the embeddings encode more gender information, and their attention is more diverted. Both behaviors help in mitigating gender bias.
Click here to access the article.

Vanmassenhove et al. (2021): Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation
Abstract Recent studies in the field of Machine Translation (MT) and Natural Language Processing (NLP) have shown that existing models amplify biases observed in the training data. The amplification of biases in language technology has mainly been examined with respect to specific phenomena, such as gender bias. In this work, we go beyond the study of gender in MT and investigate how bias amplification might affect language in a broader sense. We hypothesize that the ‘algorithmic bias’, i.e. an exacerbation of frequently observed patterns in combination with a loss of less frequent ones, not only exacerbates societal biases present in current datasets but could also lead to an artificially impoverished language: ‘machine translationese’. We assess the linguistic richness (on a lexical and morphological level) of translations created by different data-driven MT paradigms – phrase-based statistical (PB-SMT) and neural MT (NMT). Our experiments show that there is a loss of lexical and syntactic richness in the translations produced by all investigated MT paradigms for two language pairs (EN-FR and EN-ES).
Click here to access the article.

Levy et al. (2021): Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation
Abstract Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manually verify the quality of our corpus and use it to evaluate gender bias in various coreference resolution and machine translation models. We find that all tested models tend to over-rely on gender stereotypes when presented with natural inputs, which may be especially harmful when deployed in commercial systems. Finally, we show that our dataset lends itself to finetuning a coreference resolution model, finding it mitigates bias on a held out set. Our dataset and models are publicly available at github.com/SLAB-NLP/BUG. We hope they will spur future research into gender bias evaluation mitigation techniques in realistic settings.
Click here to access the article.

Troles and Schmid (2021): Extending Challenge Sets to Uncover Gender Bias in Machine Translation. Impact of Stereotypical Verbs and Adjectives
Abstract 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 when occupations are translated from a language like English, which mostly uses gender neutral words, to a language like German, which mostly uses a feminine and a masculine version for an occupation, a decision must be made by the MT System. Recent research showed that MT systems are biased towards stereotypical translation of occupations. In 2019 the first, and so far only, challenge set, explicitly designed to measure the extent of gender bias in MT systems has been published. In this set measurement of gender bias is solely based on the translation of occupations. With our paper we present an extension of this challenge set, called WiBeMT, which adds gender-biased adjectives and sentences with gender-biased verbs. The resulting challenge set consists of over 70, 000 sentences and has been translated with three commercial MT systems: DeepL Translator, Microsoft Translator, and Google Translate. Results show a gender bias for all three MT systems. This gender bias is to a great extent significantly influenced by adjectives and to a lesser extent by verbs.
Click here to access the article.

Blodgett et al. (2020): Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Abstract We survey 146 papers analyzing “bias” in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing “bias” is an inherently normative process. We further find that these papers’ proposed quantitative techniques for measuring or mitigating “bias” are poorly matched to their motivations and do not engage with the relevant literature outside of NLP. Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing “bias” in NLP systems. These recommendations rest on a greater recognition of the relationships between language and social hierarchies, encouraging researchers and practitioners to articulate their conceptualizations of “bias”---i.e., what kinds of system behaviors are harmful, in what ways, to whom, and why, as well as the normative reasoning underlying these statements—and to center work around the lived experiences of members of communities affected by NLP systems, while interrogating and reimagining the power relations between technologists and such communities.
Click here to access the article.

Stafanovičs et al. (2020): Mitigating Gender Bias in Machine Translation with Target Gender Annotations” in NLP
Abstract When translating “The secretary asked for details.” to a language with grammatical gender, it might be necessary to determine the gender of the subject “secretary”. If the sentence does not contain the necessary information, it is not always possible to disambiguate. In such cases, machine translation systems select the most common translation option, which often corresponds to the stereotypical translations, thus potentially exacerbating prejudice and marginalisation of certain groups and people. We argue that the information necessary for an adequate translation can not always be deduced from the sentence being translated or even might depend on external knowledge. Therefore, in this work, we propose to decouple the task of acquiring the necessary information from the task of learning to translate correctly when such information is available. To that end, we present a method for training machine translation systems to use word-level annotations containing information about subject’s gender. To prepare training data, we annotate regular source language words with grammatical gender information of the corresponding target language words. Using such data to train machine translation systems reduces their reliance on gender stereotypes when information about the subject’s gender is available. Our experiments on five language pairs show that this allows improving accuracy on the WinoMT test set by up to 25.8 percentage points.
Click here to access the article.

Kocmi et al. (2020): Gender Coreference and Bias Evaluation at WMT 2020
Abstract Gender 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 particularly harmful as models become more popular and deployed within commercial systems. Our work presents the largest evidence for the phenomenon in more than 19 systems submitted to the WMT over four diverse target languages: Czech, German, Polish, and Russian. To achieve this, we use WinoMT, a recent automatic test suite which examines gender coreference and bias when translating from English to languages with grammatical gender. We extend WinoMT to handle two new languages tested in WMT: Polish and Czech. We find that all systems consistently use spurious correlations in the data rather than meaningful contextual information.
Click here to access the article.

Cao and Daume III (2020): Toward gender-inclusive coreference resolution
Abstract Correctly 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 binary and non-binary trans and cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations of gender from sociology and sociolinguistics, and develop two new datasets for interrogating bias in crowd annotations and in existing coreference resolution systems. Through these studies, conducted on English text, we confirm that without acknowledging and building systems that recognize the complexity of gender, we build systems that lead to many potential harms.
Click here to access the article.

Alhafni et al. (2020): Gender-aware reinflection using linguistically enhanced neural models
Abstract In this paper, we present an approach for sentence-level gender reinflection using linguistically enhanced sequence-to-sequence models. Our system takes an Arabic sentence and a given target gender as input and generates a gender-reinflected sentence based on the target gender. We formulate the problem as a user-aware grammatical error correction task and build an encoder-decoder architecture to jointly model reinflection for both masculine and feminine grammatical genders. We also show that adding linguistic features to our model leads to better reinflection results. The results on a blind test set using our best system show improvements over previous work, with a 3.6% absolute increase in M2 F0.5.
Click here to access the article.

Bentivogli et al. (2020): Gender in danger? Evaluating speech translation technology on the MuST-SHE Corpus
Abstract Translating 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 on which models are built typically reflect the asymmetries of natural languages, gender bias included. Exclusively fed with textual data, machine translation is intrinsically constrained by the fact that the input sentence does not always contain clues about the gender identity of the referred human entities. But what happens with speech translation, where the input is an audio signal? Can audio provide additional information to reduce gender bias? We present the first thorough investigation of gender bias in speech translation, contributing with: i) the release of a benchmark useful for future studies, and ii) the comparison of different technologies (cascade and end-to-end) on two language directions (English-Italian/French).
Click here to access the article.

Font and Costa-Jussà (2019): Equalizing Gender Bias in Neural Machine Translation with Word Embedding Techniques.
Abstract 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 contain biases and stereotypes. As a consequence, models inherit these social biases. Recent methods have shown results in reducing gender bias in other natural language processing tools such as word embeddings. We take advantage of the fact that word embeddings are used in neural machine translation to propose a method to equalize gender biases in neural machine translation using these representations. Specifically, we propose, experiment and analyze the integration of two debiasing techniques over GloVe embeddings in the Transformer translation architecture. We evaluate our proposed system on the WMT English-Spanish benchmark task, showing gains up to one BLEU point. As for the gender bias evaluation, we generate a test set of occupations and we show that our proposed system learns to equalize existing biases from the baseline system.
Click here to access the article.

Cho et al. (2019): On measuring gender bias in translation of gender-neutral pronouns
Abstract Ethics regarding social bias has recently thrown striking issues in natural language processing. Especially for gender-related topics, the need for a system that reduces the model bias has grown in areas such as image captioning, content recommendation, and automated employment. However, detection and evaluation of gender bias in the machine translation systems are not yet thoroughly investigated, for the task being cross-lingual and challenging to define. In this paper, we propose a scheme for making up a test set that evaluates the gender bias in a machine translation system, with Korean, a language with gender-neutral pronouns. Three word/phrase sets are primarily constructed, each incorporating positive/negative expressions or occupations; all the terms are gender-independent or at least not biased to one side severely. Then, additional sentence lists are constructed concerning formality of the pronouns and politeness of the sentences. With the generated sentence set of size 4,236 in total, we evaluate gender bias in conventional machine translation systems utilizing the proposed measure, which is termed here as translation gender bias index (TGBI). The corpus and the code for evaluation is available on-line.
Click here to access the article.

Zhou et al. (2019): Examining Gender Bias in Languages with Grammatical Gender
Abstract Recent 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 English. These analyses cannot be directly extended to languages that exhibit morphological agreement on gender, such as Spanish and French. In this paper, we propose new metrics for evaluating gender bias in word embeddings of these languages and further demonstrate evidence of gender bias in bilingual embeddings which align these languages with English. Finally, we extend an existing approach to mitigate gender bias in word embedding under both monolingual and bilingual settings. Experiments on modified Word Embedding Association Test, word similarity, word translation, and word pair translation tasks show that the proposed approaches effectively reduce the gender bias while preserving the utility of the embeddings.
Click here to access the article.

Rudinger et al. (2018): Gender Bias in Coreference Resolution
Abstract We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these “Winogender schemas,” we evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems, and correlate this bias with real-world and textual gender statistics.
Click here to access the article.

Caliskan et al. (2017): Semantics derived automatically from language corpora contain human-like biases
Abstract Machine learning is a means to derive artificial intelligence by discovering patterns in existing data. Here we show that applying machine learning to ordinary human language results in human-like semantic biases. We replicate a spectrum of known biases, as measured by the Implicit Association Test, using a widely used, purely statistical machine-learning model trained on a standard corpus of text from the Web. Our results indicate that text corpora contain re-coverable and accurate imprints of our historic biases, whether morally neutral as towards insects or flowers, problematic as towards race or gender, or even simply veridical, reflecting the status quo distribution of gender with respect to careers or first names. Our methods hold promise for identifying and addressing sources of bias in culture, including technology.
Click here to access the article.

Rabinovich et al. (2017): Personalized Machine Translation: Preserving Original Author Traits
Abstract The language that we produce reflects our personality, and various personal and demographic characteristics can be detected in natural language texts. We focus on one particular personal trait of the author, gender, and study how it is manifested in original texts and in translations. We show that author’s gender has a powerful, clear signal in originals texts, but this signal is obfuscated in human and machine translation. We then propose simple domain-adaptation techniques that help retain the original gender traits in the translation, without harming the quality of the translation, thereby creating more personalized machine translation systems.
Click here to access the article.