UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Multi-objective search for gender-fair and semantically correct word embeddings

Hort, Max; Moussa, Rebecca; Sarro, Federica; (2023) Multi-objective search for gender-fair and semantically correct word embeddings. Applied Soft Computing , 133 , Article 109916. 0.1016/j.asoc.2022.109916. Green open access

[thumbnail of Hort_Multi-objective search for gender-fair and semantically correct word embeddings_VoR.pdf]
Preview
Text
Hort_Multi-objective search for gender-fair and semantically correct word embeddings_VoR.pdf

Download (1MB) | Preview

Abstract

Fairness is a crucial non-functional requirement of modern software systems that rely on the use of Artificial Intelligence (AI) to make decisions regarding our daily lives in application domains such as justice, healthcare and education. In fact, these algorithms can exhibit unwanted discriminatory behaviours that create unfair outcomes when the software is used, such as giving privilege to one group of users over another (e.g., males vs. females). Mitigating algorithmic bias during the development life cycle of AI-enabled software is crucial given that any bias in these algorithms is inherited by the software systems using them. However, previous work has shown that mitigating bias can impact the performance of such systems. Therefore, we propose herein a novel use of soft computing for improving AI-enabled software fairness. Specifically, we exploit multi-objective search, as opposed to previous work optimising fairness only, to strike an optimal balance between reducing gender bias and improving semantic correctness of word embedding models, which are at the core of many AI-enabled systems. To assess the effectiveness of our proposal, we carry out a thorough empirical study based on the most recent best practice for the evaluation of search-based approaches and AI-enabled software. We explore seven different search-based approaches, and benchmark them against both baseline and state-of-the-art approaches applied to a popular and widely used word embedding model, namely Word2Vec. Our results show that multi-objective search outperforms single-objective search, and generates word embeddings that are strictly better than the original ones in both objectives, bias and semantic correctness, for all investigated cases. Additionally, our approach generates word embeddings of higher semantic correctness than those generated by using state-of-the-art techniques in all cases, while also achieving a higher degree of fairness in 67% of the cases. These findings show the feasibility and effectiveness of multi-objective search as a tool for engineers to incorporate fair and accurate word embedding models in their AI-enabled systems.

Type: Article
Title: Multi-objective search for gender-fair and semantically correct word embeddings
Open access status: An open access version is available from UCL Discovery
DOI: 0.1016/j.asoc.2022.109916
Publisher version: https://doi.org/10.1016/j.asoc.2022.109916
Language: English
Additional information: © 2022 The Author(s). Published by Elsevier B.V. under a Creative Commons license (http://creativecommons.org/licenses/by/4.0/).
Keywords: Software fairness, Search-based software engineering, Gender biasWord embeddings
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10161490
Downloads since deposit
22Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item