Learning Gender-Neutral Word Embeddings

Zhao, Jieyu; Zhou, Yichao; Li, Zeyu; Wang, Wei; Chang, Kai-Wei

doi:10.18653/v1/d18-1521

Cited by 270 publications

(322 citation statements)

References 32 publications

Supporting

Mentioning

319

Contrasting

Unclassified

Order By: Relevance

“…Our work is closely related to the line of work on removing bias in data representations. Bolukbasi et al (2016); Zhao et al (2018b) learn gender-neutral word embeddings by forcing certain dimensions to be free of gender information. Similarly, construct a biased classifier and project its representation out of the model's representation.…”

Section: Related Work and Discussionmentioning

confidence: 99%

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

He¹,

Zha²,

Wang³

2019

Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)

112

142

View full text Add to dashboard Cite

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate contradiction. As exposed by several recent challenge datasets, these models perform poorly when such association is absent, e.g., predicting that "I love dogs." contradicts "I don't love cats.". Our goal is to design learning algorithms that guard against known dataset bias. We formalize the concept of dataset bias under the framework of distribution shift and present a simple debiasing algorithm based on residual fitting, which we call DRiFt. We first learn a biased model that only uses features that are known to relate to dataset bias. Then, we train a debiased model that fits to the residual of the biased model, focusing on examples that cannot be predicted well by biased features only. We use DRiFt to train three high-performing NLI models on two benchmark datasets, SNLI and MNLI. Our debiased models achieve significant gains over baseline models on two challenge test sets, while maintaining reasonable performance on the original test sets.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

He¹,

Zha²,

Wang³

2019

Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)

112

142

View full text Add to dashboard Cite

show abstract

“…For coreference resolution, Rudinger et al (2018) and Zhao et al (2018b) independently designed GBETs based on Winograd Schemas. The corpus consists of sentences which contain a gender-neutral occupation (e.g., doctor), a secondary participant (e.g., patient), and a gendered pronoun that refers either the occupation or the participant.…”

Section: Taskmentioning

confidence: 99%

“…Ultimately, word embeddings with reduced bias performed just as well as unaltered embeddings on coherence and analogy-solving tasks (Bolukbasi et al, 2016). Zhao et al (2018b) propose a new method called GN-GloVe that does not use a classifier to create a set of gender-specific words. The authors train the word embeddings by isolating gender information in specific dimensions and maintaining gender-neutral information in the other dimensions.…”

Section: Removing Gender Subspace In Word Embeddingsmentioning

confidence: 99%

Mitigating Gender Bias in Natural Language Processing: Literature Review

Sun¹,

Gaut²,

Tang³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

272

225

View full text Add to dashboard Cite

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

show abstract

“…Caliskan et al (2017) formulate a method to test biases (including gender stereotypes) in word embeddings, while Rudinger et al (2018) investigate such stereotypes in the context of coreference resolution. There have also been efforts to debias word embeddings (Bolukbasi et al, 2016) and come up with gender neutral word embeddings (Zhao et al, 2018). These efforts, however, have attracted criticism suggesting that they do not actually debias embeddings but instead redistribute the bias across the embedding landscape (Gonen and Goldberg, 2019).…”

Section: Prior Workmentioning

confidence: 99%

Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis

Bhaskaran¹,

Bhallamudi²

2019

Proceedings of the First Workshop on Gender Bias in Natural Language Processing

View full text Add to dashboard Cite

In this work, we investigate the presence of occupational gender stereotypes in sentiment analysis models. Such a task has implications for reducing implicit biases in these models, which are being applied to an increasingly wide variety of downstream tasks. We release a new gender-balanced dataset 1 of 800 sentences pertaining to specific professions and propose a methodology for using it as a test bench to evaluate sentiment analysis models. We evaluate the presence of occupational gender stereotypes in 3 different models using our approach, and explore their relationship with societal perceptions of occupations.

show abstract

Learning Gender-Neutral Word Embeddings

Cited by 270 publications

References 32 publications

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

Mitigating Gender Bias in Natural Language Processing: Literature Review

Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis

Contact Info

Product

Resources

About