[Day59] 임베딩내 편향성 알아보자

임베딩내 편향성이라는 것을 처음 들었을 때는 무슨 뜻인지 잘 이해하지 못했지만, 알아보니 AI가 학습하는 자연어 데이타가 편향성을 가지고 있다면, AI의 동작이 편향적일 수 있다는 그런 내용이었습니다. 읽어보면 좋을 내용들을 공유합니다.

1. Predictive policing algorithms are racist. They need to be dismantled.

www.technologyreview.com/2020/07/17/1005396/predictive-policing-algorithms-racist-dismantled-machine-learning-bias-criminal-justice/

Predictive policing algorithms are racist. They need to be dismantled.

2. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (paper)

arxiv.org/pdf/1607.06520.pdf

3. Semantics derived automatically from language corpora necessarily contain human biases (paper)

arxiv.org/pdf/1608.07187.pdf

4. Project Implicit

implicit.harvard.edu/implicit/education.html

Education

5. Text Embedding Models Contain Bias. Here's Why That Matters.

developers.googleblog.com/2018/04/text-embedding-models-contain-bias.html

Text Embedding Models Contain Bias. Here's Why That Matters.

6. Google WEAT (data)

drive.google.com/u/0/uc?id=0B7XkCwpI5KDYNlNUTTlSS21pQmM&export=download

Google 드라이브 - 바이러스 검사 경고

7. Synosis data

aiffelstaticprd.blob.core.windows.net/media/documents/synopsis.zip

8. TF-IDF(Term Frequency-Inverse Document Frequency)

wikidocs.net/31698

위키독스