Quantifying and Debiasing Gender Bias in Japanese Gender-specific Words with Word Embedding

Leisi Chen, Toru Sugimoto

研究成果: Conference contribution

抄録

Machine Learning is playing a significant role in modern life. However, the problem that Machine Learning has biases and stereotypes has also drawn the researcher's attention. Word2Vec, a popular framework in the NLP field to encode the word's meaning as a real-valued vector, has been used in many machine learning and natural language processing tasks. Still, it also has been proved that it contains severe biases toward women. In this paper, we used Word2Vec to analyze the relationship between gender-specific words and personality adjectives in Japanese to Figure out the latent gender bias in those gender-specific words. We first found that the Word2Vec model trained by Japanese Wikipedia data shows that some occupation gender-specific words strongly connect with negative personality adjectives. The experiment results reflect that people commonly use these gender-specific words to criticize women in these specific occupations. Then we eliminated the projection of word vectors of personality adjectives on the gender subspace and reduced the relationship between negative personality adjectives and gender-specific words by word vector calculation.

本文言語English
ホスト出版物のタイトル2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781665499248
DOI
出版ステータスPublished - 2022
イベントJoint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2022 - Ise, Japan
継続期間: 2022 11月 292022 12月 2

出版物シリーズ

名前2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2022

Conference

ConferenceJoint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2022
国/地域Japan
CityIse
Period22/11/2922/12/2

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • 制御と最適化
  • モデリングとシミュレーション
  • 数値解析

フィンガープリント

「Quantifying and Debiasing Gender Bias in Japanese Gender-specific Words with Word Embedding」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル