Multi-Dimensional Gender Bias Classification
| Autor: | Ledell Wu, Jason Weston, Angela Fan, Emily Dinan, Douwe Kiela, Adina Williams |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language ComputingMilieux_THECOMPUTINGPROFESSION Computer science business.industry 02 engineering and technology 010501 environmental sciences Variety (linguistics) computer.software_genre 01 natural sciences Machine models 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Gender bias Multi dimensional 020201 artificial intelligence & image processing Artificial intelligence Scale (map) business computer Computation and Language (cs.CL) Natural language processing Generative grammar 0105 earth and related environmental sciences |
| Zdroj: | EMNLP (1) |
| DOI: | 10.48550/arxiv.2005.00614 |
| Popis: | Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions: bias from the gender of the person being spoken about, bias from the gender of the person being spoken to, and bias from the gender of the speaker. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information. In addition, we collect a novel, crowdsourced evaluation benchmark of utterance-level gender rewrites. Distinguishing between gender bias along multiple dimensions is important, as it enables us to train finer-grained gender bias classifiers. We show our classifiers prove valuable for a variety of important applications, such as controlling for gender bias in generative models, detecting gender bias in arbitrary text, and shed light on offensive language in terms of genderedness. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|