{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-measuring-social-biases-in-sentence","title":"On Measuring Social Biases in Sentence Encoders","arxiv_id":"1903.10561","date":"2019-03-25","proceeding":"NAACL 2019 6","authors":["Chandler May","Alex Wang","Shikha Bordia","Samuel R. Bowman","Rachel Rudinger"],"abstract":"The Word Embedding Association Test shows that GloVe and word2vec word\nembeddings exhibit human-like implicit biases based on gender, race, and other\nsocial constructs (Caliskan et al., 2017). Meanwhile, research on learning\nreusable text representations has begun to explore sentence-level texts, with\nsome sentence encoders seeing enthusiastic adoption. Accordingly, we extend the\nWord Embedding Association Test to measure bias in sentence encoders. We then\ntest several sentence encoders, including state-of-the-art methods such as ELMo\nand BERT, for the social biases studied in prior work and two important biases\nthat are difficult or impossible to test at the word level. We observe mixed\nresults including suspicious patterns of sensitivity that suggest the test's\nassumptions may not hold in general. We conclude by proposing directions for\nfuture work on measuring bias in sentence encoders.","url_abs":"http://arxiv.org/abs/1903.10561v1","url_pdf":"http://arxiv.org/pdf/1903.10561v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-measuring-social-biases-in-sentence","repo_url":"https://github.com/W4ngatang/sent-bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glove","method_name":"GloVe"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.10561","atlas_url":"https://app.syntology.ai/?focus=1903.10561","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}