Sesari, Emeralda;
Hort, Max;
Sarro, Federica;
(2022)
An Empirical Study on the Fairness of Pre-trained Word Embeddings.
In:
Proceedings of the Fourth Workshop on Gender Bias in Natural Language Processing.
ACL
(In press).
Preview |
Text
ACL___Word_Embedding_Bias.pdf - Other Download (437kB) | Preview |
Abstract
Pre-trained word embedding models are easily distributed and applied, as they alleviate users from the effort to train models themselves. With widely distributed models, it is important to ensure that they do not exhibit undesired behaviour, such as biases against population groups. For this purpose, we carry out an empirical study on evaluating the bias of 15 publicly available, pre-trained word embeddings model based on three training algorithms (GloVe, word2vec, and fastText) with regard to four bias metrics (WEAT, SEMBIAS, DIRECT BIAS, and ECT). The choice of word embedding models and bias metrics is motivated by a literature survey over 37 publications which quantified bias on pre-trained word embeddings. Our results indicate that fastText is the least biased model (in 8 out of 12 cases) and small vector lengths lead to a higher bias.
| Type: | Proceedings paper |
|---|---|
| Title: | An Empirical Study on the Fairness of Pre-trained Word Embeddings |
| Event: | 4th Workshop on Gender Bias in Natural Language Processing |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://aclanthology.org/ |
| Language: | English |
| Additional information: | The article is licensed on a Creative Commons Attribution 4.0 International License. |
| UCL classification: | 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 UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10149529 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
