This paper studies dialogue response selection task. As state-of-the-arts are neural models requiring a large training set, data augmentation is essential to overcome the sparsity of observational annotation, where one observed response is annotated as gold. In this paper, we propose counterfactual augmentation, of considering whether unobserved utterances would “counterfactually” replace the labelled response, for the given context, and augment only if that is the case. We empirically show that our pipeline improves BERT-based models in two different response selection tasks without incurring annotation overheads.
|Number of pages||5|
|Journal||Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH|
|Publication status||Published - 2020|
|Event||21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China|
Duration: 2020 Oct 25 → 2020 Oct 29
Bibliographical noteFunding Information:
This work is supported by AI Graduate School Program (2020-0-01361) and IITP grant (No.2017-0-01779, XAI) supervised by IITP. Hwang is a corresponding author.
Copyright © 2020 ISCA
All Science Journal Classification (ASJC) codes
- Language and Linguistics
- Human-Computer Interaction
- Signal Processing
- Modelling and Simulation