Automatic Gender Identification and Reinflection in Arabic

By Nizar Habash, Houda Bouamor, Christine Chung. 2019

53 citations recorded by the source corpus.

The impressive progress in many Natural Language Processing (NLP) applications has increased the awareness of some of the biases these NLP systems have with regards to gender identities. In this paper, we propose an approach to extend biased single-output gender-blind NLP systems with gender-specific alternative reinflections. We focus on Arabic, a gender-marking morphologically rich language, in the context of machine translation (MT) from English, and for first-person-singular constructions only. Our contributions are the development of a system-independent gender-awareness wrapper, and the building of a corpus for training and evaluating first-person-singular gender identification and reinflection in Arabic. Our results successfully demonstrate the viability of this approach with 8% relative increase in Bleu score for first-person-singular feminine, and 5.3% comparable increase for first-person-singular masculine on top of a state-of-the-art gender-blind MT system on a held-out test set.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Societal Biases in Language Generation: Progress and Challenges (2021, methodology): “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 ”
Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation (2020, background): “Most similar to our current work, Habash et al. (2019); Moryossef et al.”
Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, background): “2019), uncovering many gender disparities and harmful biases in algorithms and text (Cao and Daumé III 2020; Chang et al. 2019; 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”
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology (2019, background): “Habash et al. (2019) also focused on morphologically rich languages, specifically Arabic, but in the context of gender identification in machine translation.”
What do Bias Measures Measure? (2021, methodology): “, Habash et al. (2019) build a corpus for gender reinflection in Arabic, Zmigrod et al.”
Gender Bias in Machine Translation (2021, methodology): “The Arabic Parallel Gender Corpus (Habash et al., 2019) includes an English-Arabic test set13 retrieved from OpenSubtitles natural language data (Lison and Tiedemann, 2016).”
Mitigating Gender Bias in Machine Translation with Target Gender Annotations (2020, background): “Habash et al. (2019) approach this as a gender classiﬁcation and reinﬂection task for target language sentences to address the ﬁrst person singular cases when translating from English into Arabic.”
Perturbation Augmentation for Fairer NLP (2022, methodology): “…gender, has already been used to combat bias arising from morphological underspecifi-cation during automatic translation for languages with more grammatical gender morphology than English, including Arabic (Habash et al., 2019; Alhafni et al., 2020) and Italian (Vanmassenhove and Monti, 2021).”
First the Worst: Finding Better Gender Translations During Beam Search (2021, background): “Related approaches083 for monolingual tasks reinflect whole-sentence gen-084 der (Habash et al., 2019; Alhafni et al., 2020; Sun085 et al., 2021).”
AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings (2020, background): “While their is some effort to account for genderawareness in Arabic machine translation (Habash et al., 2019), we are, to the best of our knowledge, the first to measure bias in Arabic Language Technology.”
Theories of “Gender” in NLP Bias Research (2022, background): “14065 [58] Nizar Habash, Houda Bouamor, and Christine Chung.”
Gender-Aware Reinflection using Linguistically Enhanced Neural Models (2020, methodology): “In this paper, we follow Habash et al. (2019)’s decision to evaluate within an orthographically normalized space for Alif, Ya, and Ta-Marbuta, since the OpenSubtitles 2018 corpus (Lison and Tiedemann, 2016) they use to build the Arabic parallel gender corpus has many of such spelling confusions.”