Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
Meeting of the Association for Computational Linguistics, 2019.
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization performance of trained models and give untrustworthy evaluation results. For many NLSM datasets, the provide...More
PPT (Upload PPT)