Abstract
With the vast development and employment of artificial intelligence applications, research into the fairness of these algorithms has been increased. Specifically, in the natural language processing domain, it has been shown that social biases persist in word embeddings and are thus in danger of amplifying these biases when used. As an example of social bias, religious biases are shown to persist in word embeddings and the need for its removal is highlighted. This paper investigates the state-of-the-art multiclass debiasing techniques: Hard debiasing, SoftWEAT debiasing and Conceptor debiasing. It evaluates their performance when removing religious bias on a common basis by quantifying bias removal via the Word Embedding Association Test (WEAT), Mean Average Cosine Similarity (MAC) and the Relative Negative Sentiment Bias (RNSB). By investigating the religious bias removal on three widely used word embeddings, namely: Word2Vec, GloVe, and ConceptNet, it is shown that the preferred method is ConceptorDebiasing. Specifically, this technique manages to decrease the measured religious bias on average by 82.42%, 96.78% and 54.76% for the three word embedding sets respectively.
Original language | English |
---|---|
Title of host publication | Artificial Intelligence and Machine Learning - 32nd Benelux Conference, BNAIC/Benelearn 2020, Revised Selected Papers |
Editors | Mitra Baratchi, Lu Cao, Walter A. Kosters, Jefrey Lijffijt, Jan N. van Rijn, Frank W. Takes |
Publisher | Springer |
Pages | 141-156 |
Number of pages | 16 |
Volume | 1398 CCIS |
ISBN (Print) | 9783030766399 |
DOIs | |
Publication status | Published - 1 Jan 2021 |
Event | 32nd Benelux Conference on Artificial Intelligence and Belgian-Dutch Conference on Machine Learning - Online, Leiden, Netherlands Duration: 19 Nov 2020 → 20 Nov 2020 Conference number: 32 https://bnaic.liacs.leidenuniv.nl/ |
Publication series
Series | Communications in Computer and Information Science |
---|---|
Volume | 1398 CCIS |
ISSN | 1865-0929 |
Conference
Conference | 32nd Benelux Conference on Artificial Intelligence and Belgian-Dutch Conference on Machine Learning |
---|---|
Abbreviated title | BNAIC/BeNeLearn 2020 |
Country/Territory | Netherlands |
City | Leiden |
Period | 19/11/20 → 20/11/20 |
Internet address |
Keywords
- Natural language processing
- Social bias
- Word embeddings