Gender bias in legal corpora and debiasing it

Simple item page
buir.contributor.authorKoç, Aykut
buir.contributor.authorSevim, Nurullah
buir.contributor.authorŞahinuç, Furkan
dc.citation.epage34en_US
dc.citation.spage1en_US
dc.contributor.authorKoç, Aykut
dc.contributor.authorSevim, Nurullah
dc.contributor.authorŞahinuç, Furkan
dc.date.accessioned2023-02-16T07:02:36Z
dc.date.available2023-02-16T07:02:36Z
dc.date.issued2022-03-30
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentNational Magnetic Resonance Research Center (UMRAM)en_US
dc.description.abstractWord embeddings have become important building blocks that are used profoundly in natural language processing (NLP). Despite their several advantages, word embeddings can unintentionally accommodate some gender- and ethnicity-based biases that are present within the corpora they are trained on. Therefore, ethical concerns have been raised since word embeddings are extensively used in several high-level algorithms. Studying such biases and debiasing them have recently become an important research endeavor. Various studies have been conducted to measure the extent of bias that word embeddings capture and to eradicate them. Concurrently, as another subfield that has started to gain traction recently, the applications of NLP in the field of law have started to increase and develop rapidly. As law has a direct and utmost effect on people’s lives, the issues of bias for NLP applications in legal domain are certainly important. However, to the best of our knowledge, bias issues have not yet been studied in the context of legal corpora. In this article, we approach the gender bias problem from the scope of legal text processing domain. Word embedding models that are trained on corpora composed by legal documents and legislation from different countries have been utilized to measure and eliminate gender bias in legal documents. Several methods have been employed to reveal the degree of gender bias and observe its variations over countries. Moreover, a debiasing method has been used to neutralize unwanted bias. The preservation of semantic coherence of the debiased vector space has also been demonstrated by using high-level tasks. Finally, overall results and their implications have been discussed in the scope of NLP in legal domain.en_US
dc.identifier.doi10.1017/S1351324922000122en_US
dc.identifier.eissn1469-8110
dc.identifier.issn1351-3249
dc.identifier.urihttp://hdl.handle.net/11693/111389
dc.language.isoEnglishen_US
dc.publisherCambridge University Pressen_US
dc.relation.isversionofhttp://dx.doi.org/10.1017/S1351324922000122en_US
dc.source.titleNatural Language Engineeringen_US
dc.subjectBiasen_US
dc.subjectNLP in lawen_US
dc.subjectLegal text processingen_US
dc.subjectLawen_US
dc.subjectComputational lawen_US
dc.titleGender bias in legal corpora and debiasing iten_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gender_bias_in_legal_corpora_and_debiasing_it.pdf
Size:
1.47 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

National Magnetic Resonance Research Center (UMRAM)
Department of Electrical and Electronics Engineering