Automatic Gender Identification and Reinflection in Arabic

Habash, Nizar; Bouamor, Houda; Chung, Christine H.

doi:10.18653/v1/w19-3822

Cited by 32 publications

(45 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach is specifically intended to yield grammatical sentences when applied to such languages. Habash et al (2019) also focused on morphologically rich languages, specifically Arabic, but in the context of gender identification in machine translation.…”

Section: Related Workmentioning

confidence: 99%

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Zmigrod¹,

Mielke²,

Wallach³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

158

122

View full text Add to dashboard Cite

Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages. We present a novel approach for converting between masculine-inflected and feminineinflected sentences in such languages. For Spanish and Hebrew, our approach achieves F 1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms. By evaluating our approach using four different languages, we show that, on average, it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality.

show abstract

Section: Related Workmentioning

confidence: 99%

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Zmigrod¹,

Mielke²,

Wallach³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

158

122

View full text Add to dashboard Cite

show abstract

“…Curated Datasets Existing datasets to study biases in translation include parallel sentences tagged with speaker or subject gender information ( Vanmassenhove et al, 2018;Habash et al, 2019) and datasets to study gender biases when translating from neutral references of a person (e.g., nurse in English, gender-neutral pronouns) to gendered instances (e.g., enfermera or enfermero in Spanish, gendered pronouns) Stanovsky et al, 2019;Gonen and Webster, 2020;Kocmi et al, 2020). Renduchintala and Williams (2021) additionally provide a dataset to study translation of neutral references in unambiguous contexts.…”

Section: Data Methodsmentioning

confidence: 99%

“…Examples of evaluation objectives through absolute scores include reducing non-normative generations, Ma et al (2020) increasing the accuracy of the change in agency, Zmigrod et al (2019) increasing the number of correct inflections, Huang et al (2020) reducing individual and group fairness scores, and Sheng et al (2021b) reducing the amount of ad hominems towards marginalized groups. Studies of gender bias in machine translation are well-suited to evaluations using absolute scores: many use BLEU and its variants to evaluate correct gender inflections and translations (Moryossef et al, 2019;Escudé Font and Costajussà, 2019;Elaraby et al, 2018;Habash et al, 2019;Alhafni et al, 2020) or accuracy on WinoMT Kocmi et al, 2020;Costa-jussà and de Jorge, 2020;Choubey et al, 2021;. Relative Evaluations In terms of evaluation through relative scores, examples from existing works are mainly from continuation generation tasks.…”

Section: Evaluation Methodsmentioning

confidence: 99%

“…While Google Translate 3 has been the most popular commercial system to analyze for gender biases (Prates et al, 2019;Moryossef et al, 2019;Stanovsky et al, 2019;Farkas and Németh, 2020), Stanovsky et al (2019) Re-writing We use the term re-writing to refer to tasks of revising specific words and phrases in the original text to be more aligned with a targeted attribute. Specifically, there have been studies on re-inflection (Habash et al, 2019;Zmigrod et al, 2019;Alhafni et al, 2020) and re-writing text to use neutral viewpoints (Pryzant et al, 2020), genderneutral English , or more agency (Ma et al, 2020). These tasks typically rely on custom encoder-decoder models.…”

Section: Transformation Generation Tasksmentioning

confidence: 99%

See 1 more Smart Citation

Societal Biases in Language Generation: Progress and Challenges

Sheng

Chang

Natarajan

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can effectively generate fluent text, they can also produce undesirable societal biases that can have a disproportionately negative impact on marginalized populations. Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques. To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases. Motivated by a lack of studies on biases from decoding techniques, we also conduct experiments to quantify the effects of these techniques. By further discussing general trends and open challenges, we call to attention promising directions for research and the importance of fairness and inclusivity considerations for language generation applications.

show abstract

“…Recently, the NLP community has focused on exploring gender bias in NLP systems (Sun et al, 2019), uncovering many gender disparities and harmful biases in algorithms and text (Cao and Chang and McKeown 2019;Costa-jussà 2019;Du et al 2019;Emami et al 2019;Garimella et al 2019;Gaut et al 2020;Habash et al 2019;Hashempour 2019;Hoyle et al 2019;Lee et al 2019a;Lepp 2019;Qian 2019;Sharifirad and Matwin 2019;Stanovsky et al 2019;O'Neil 2016;Blodgett et al 2020;Nangia et al 2020). Particular attention has been paid to uncovering, analyzing, and removing gender biases in word embeddings (Basta et al, 2019;Kaneko and Bollegala, 2019;Zhao et al, , 2018bBolukbasi et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan

Fan

Williams

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

105

View full text Add to dashboard Cite

Social 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 is not only replicated, but is also amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets before selecting the most biased one, the multi-player textbased fantasy adventure dataset LIGHT (Urbanek et al., 2019), as a testbed for bias mitigation techniques. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances, and find that they are particularly effective in combination. We evaluate model performance with a variety of quantitative methods-including the quantity of gendered words, a dialogue safety classifier, and human assessments-all of which show that our models generate less gendered, but equally engaging chit-chat responses.

show abstract

Automatic Gender Identification and Reinflection in Arabic

Cited by 32 publications

References 22 publications

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Societal Biases in Language Generation: Progress and Challenges

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Contact Info

Product

Resources

About