Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings
This addresses the problem of overlooked social biases in natural language processing for researchers and practitioners, though it is incremental as it extends existing bias evaluation to sense embeddings.
The paper tackled the problem of social biases in sense embeddings, which are understudied compared to word embeddings, by creating a benchmark dataset and proposing novel evaluation measures; the results showed that sense-level biases exist even when word-level biases are not detected, with specific examples indicating significant bias levels.
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior work evaluating the social biases in pretrained word embeddings, the biases in sense embeddings have been relatively understudied. We create a benchmark dataset for evaluating the social biases in sense embeddings and propose novel sense-specific bias evaluation measures. We conduct an extensive evaluation of multiple static and contextualised sense embeddings for various types of social biases using the proposed measures. Our experimental results show that even in cases where no biases are found at word-level, there still exist worrying levels of social biases at sense-level, which are often ignored by the word-level bias evaluation measures.