TY - GEN
T1 - On measuring social biases in sentence encoders
AU - May, Chandler
AU - Wang, Alex
AU - Bordia, Shikha
AU - Bowman, Samuel R.
AU - Rudinger, Rachel
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text representations has begun to explore sentence-level texts, with some sentence encoders seeing enthusiastic adoption. Accordingly, we extend the Word Embedding Association Test to measure bias in sentence encoders. We then test several sentence encoders, including state-of-the-art methods such as ELMo and BERT, for the social biases studied in prior work and two important biases that are difficult or impossible to test at the word level. We observe mixed results including suspicious patterns of sensitivity that suggest the test's assumptions may not hold in general. We conclude by proposing directions for future work on measuring bias in sentence encoders.
AB - The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text representations has begun to explore sentence-level texts, with some sentence encoders seeing enthusiastic adoption. Accordingly, we extend the Word Embedding Association Test to measure bias in sentence encoders. We then test several sentence encoders, including state-of-the-art methods such as ELMo and BERT, for the social biases studied in prior work and two important biases that are difficult or impossible to test at the word level. We observe mixed results including suspicious patterns of sensitivity that suggest the test's assumptions may not hold in general. We conclude by proposing directions for future work on measuring bias in sentence encoders.
UR - http://www.scopus.com/inward/record.url?scp=85084317230&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084317230&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084317230
T3 - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
SP - 622
EP - 628
BT - Long and Short Papers
PB - Association for Computational Linguistics (ACL)
T2 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Y2 - 2 June 2019 through 7 June 2019
ER -