A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations
Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks that rely on these biased word vectors also produce gender-biased results. While some word-embedding gender-debiasing methods have been developed, these methods mainly focus on reducing gender bias associated with gender direction and fail to reduce the gender bias presented in word embedding relations. In this paper, we design a causal and simple approach for mitigating gender bias in word vector relation by utilizing the statistical dependency between gender-definition word embeddings and gender-biased word embeddings. Our method attains state-of-the-art results on gender-debiasing tasks, lexical- and sentence-level evaluation tasks, and downstream coreference resolution tasks.
Code (1)
Tasks
Causal Inferencecoreference-resolutionCoreference ResolutionSentenceWord EmbeddingsSimilar Papers 제목 키워드 기반
Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving
With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on h…
Causal InferenceWord EmbeddingsWord SimilarityReducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function
Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. …
Data AugmentationText GenerationAddressing Both Statistical and Causal Gender Fairness in NLP Models
Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Co…
counterfactualData AugmentationFairnessMitigating Gender Bias in Depression Detection via Counterfactual Inference
Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in fema…
Causal InferenceDouble-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm…
Word Embeddings