Utterance Pair Scoring for Noisy Dialogue Data Filtering

Filtering noisy training data is one of the key approaches to improving the quality of neural network-based language generation. The dialogue research community especially suffers from a lack of less-noisy and sufficiently large data. In this work, we propose a scoring function that is specifically designed to identify low-quality utterance--response pairs to filter noisy training data. Our scoring function models the naturalness of the interconnection within dialogue pairs and their content-relatedness, which is based on previous findings in dialogue response generation and linguistics. We then demonstrate the effectiveness of our scoring function by confirming (i) the correlation between automatic scoring by the proposed function and human evaluation, and (ii) the performance of a dialogue response generator trained with filtered data. Furthermore, we experimentally confirm that our scoring function potentially works as a language-independent method.