search

shivashankarrs / classimb_fairness

5 stars 0 forks source link

Task 4 (SMOTE, hidden representation) #4

Open shivashankarrs opened 3 years ago

shivashankarrs commented 3 years ago

Implement ways to create synthetic samples (SMOTE) from hidden representations.

Related to the CIKM 2020 paper.

shivashankarrs commented 3 years ago

We will use data augmentation solutions (back-translation, MLM based sampling and any other simple approach.)

shivashankarrs commented 3 years ago

@afshinrahimi can you take lead on this task? We can discuss based on the solutions I have read so far, and shortlist few techniques/implementations to use.

shivashankarrs commented 3 years ago

Backtranslation and Language models used: https://www.aclweb.org/anthology/2020.emnlp-main.97.pdf (class imbalance)

shivashankarrs commented 3 years ago

Studies several augmentation approaches for imbalance: https://www.aclweb.org/anthology/2020.findings-emnlp.269.pdf (class imbalance)

shivashankarrs commented 3 years ago

Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations, https://arxiv.org/pdf/2001.05495.pdf (Fairness)