Debiasing Gender biased Hindi Words with Word-embedding
By A. K. Pujari, Anshuman Padhi, Anshul Jain, Mukesh K. Jadon, Vikas Kumar. 2019
31 citations recorded by the source corpus.
Word-embedding is a major machine learning technique for computational applications of languages. For a given corpus, the process of word-embedding is to embed each word onto multi-dimensional space such that semantic similarities between similar words are retained. While learning the similarity as encapsulated in the training corpus, the embedding process inadvertently captures many other inherent features present in the corpus. One such thing is the bias arising out of stereotyping present in almost all the corpus no matter how extensively used and trusted they are. We study this aspect of word-embedding in the context of Hindi language. We show that many gender-neutral words in Hindi are mapped to vectors which are inclined towards one gender or the other in multi-dimensional space. We propose a new algorithm of debiasing and demonstrate its efficacy in the context of Hindi language. Further, we build a SVM-based classifier that determines whether a gender-neutral word is classified as neutral or otherwise. We corroborate our claim with experimental results on large number of individual words. This work is first ever result on debiasing in Hindi Language and our new debiasing algorithm can be applicable in the context of any language.
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
- Su Lin Blodgett
- Hal Daumé Iii
- Hanna M. Wallach
- Solon Barocas
- Kenji Araki
- Yuki Katsumata
- Neeraja Kirtane
- Masashi Takeshita
In Natural Language Processing
- Hal Daumé Iii
- Su Lin Blodgett
- Kenji Araki
- Hanna M. Wallach
- Yuki Katsumata
- Neeraja Kirtane
- Masashi Takeshita
- V. Manushree
Citations in the corpus
- Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, background): “…Manzini et al. (2019); Maudslay et al. (2019); May et al. (2019); Mirzaev et al. (2019); Prates et al. (2019); Précenth (2019); Prost et al. (2019); Pujari et al. (2019); Qian et al. (2019); Sedoc and Ungar (2019); Stanovsky et al. (2019); Tan and Celis (2019); Zhao et al. (2019); Zhou et al.…”
- Can Existing Methods Debias Languages Other than English? First Attempt to Analyze and Mitigate Japanese Word Embeddings (2020, methodology): “, 2020) and some other languages (Sahlgren and Olsson, 2019; Pujari et al., 2019), but to the authors’ best knowledge, research regarding Japanese word embeddings does not exist.”
- Efficient Gender Debiasing of Pre-trained Indic Language Models (2022, background): “Work done in Indic languages to reduce bias was first done by Pujari et al. (2019).”
- Socially Aware Bias Measurements for Hindi Language Representations (2021, unknown): “…Ghosh et al. (2021) and Sambasivan et al. (2020) explore biases and algorithmic fairness concerning non-western contexts in machine learning and Pujari et al. (2019) focus on fairness in language technologies for Indic society by investigating binary gender associated bias in Hindi language…”
- Evaluating Gender Bias in Hindi-English Machine Translation (2021, unknown): “Pujari et al. (2019) was the first work in this area; they use geometric debiasing, where a bias subspace is first defined and the word is decomposed into two components, of which the gendered component is reduced.”