2020 · 102 citations · 16 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingStereotypingBiasGender BiasGender StereotypesNatural Language UnderstandingStereotypesWord EmbeddingsBias In Word EmbeddingsBias MitigationContextual EmbeddingsContextual Word EmbeddingsContextualized EmbeddingsGender Bias MitigationNatural Language InferenceStatic Word Embeddings
Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using the task of natural language inference. We demonstrate a reduction in invalid inferences via bias mitigation strategies on static word embeddings (GloVe). Further, we show that for gender bias, these techniques extend to contextualized embeddings when applied selectively only to the static components of contextualized embeddings (ELMo, BERT).
16
A large annotated corpus for learning natural language inference
Samuel R. Bowman, Gabor Angeli, Christopher Potts et al. · 2015 · 3.5K citations · Full text
A Decomposable Attention Model for Natural Language Inference
Ankur P. Parikh, Oscar Täckström, Dipanjan Das et al. · 2016 · 1.4K citations · Full text