Gender-Aware Reinflection using Linguistically Enhanced Neural Models

Bashar Alhafni, Nizar Habash, Houda Bouamor

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageUndefined
Title of host publicationProceedings of the Second Workshop on Gender Bias in Natural Language Processing
Place of PublicationBarcelona, Spain (Online)
PublisherAssociation for Computational Linguistics
Number of pages12
StatePublished - Dec 1 2020

Cite this