Data Augmentation for Neural Online Chat Response Selection
This work addresses the challenge of enhancing generalization in online chat response selection, but it is incremental as it applies known augmentation techniques to a specific domain.
The paper tackled the problem of improving neural dialog response selection by investigating permutation and flipping data augmentation proxies across multiple models and datasets, achieving a 1 to 3 point gain in recall-at-1 over baselines in both full-scale and small-scale settings.
Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings.