Debias Training Method of Deep Learning Sequence Model -- Take Gender Bias in Occupations of Chatbot for Example
碩士 === 國立交通大學 === 資訊學院資訊學程 === 106 === The sequential model of deep learning is commonly used to deal with Natural Language Processing (NLP) tasks. And “language” as a source of training data with human bias, e.g. racial and gender discrimination, would encode the bias into deep learning model, resu...
Main Authors: | Huang, Hui-Yu, 黃慧瑜 |
---|---|
Other Authors: | Sun, Chuen-Tsai |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/j8w6u8 |
Similar Items
-
The redundancy bias of warnings to the debias effect
by: Ming-Zhe Kuo, et al.
Published: (2011) -
Bias and Debias in Recommender System: A Survey and Future Directions
by: Chen, J., et al.
Published: (2023) -
DEBIAS FOR MYOPIC LOSS AVERSION THROUGH PERFORMANCE APPRAISAL
by: JAO CHIH YU, et al.
Published: (2003) -
Can taking the perspective of an expert debias human decisions? The case for risky and delayed gains.
by: Michal eBialek, et al.
Published: (2014-09-01) -
Implementation and assessment of an intervention to debias adolescents against causal illusions.
by: Itxaso Barberia, et al.
Published: (2013-01-01)