Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

@inproceedings{He2019UnlearnDB,
  title={Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual},
  author={He He and Sheng Zha and Haohan Wang},
  booktitle={DeepLo@EMNLP-IJCNLP},
  year={2019}
}
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… Expand
Simple but effective techniques to reduce biases
Towards Robustifying NLI Models Against Lexical Dataset Biases
Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles
End-to-End Bias Mitigation by Modelling Biases in Corpora
Learning from others' mistakes: Avoiding dataset biases without modeling them
DATASET BIASES WITHOUT MODELING THEM
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 46 REFERENCES
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
Annotation Artifacts in Natural Language Inference Data
Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Hypothesis Only Baselines in Natural Language Inference
WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale
Learning Robust Representations by Projecting Superficial Statistics Out
...
1
2
3
4
5
...