The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu, Haitao Zheng, Shuming Shi
Abstract
Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this task: each response candidate is labeled either relevant (one) or irrelevant (zero). On the one hand, this formalization can be sub-optimal due to its ignorance of the diversity of response quality. On the other hand, annotating grayscale data for learning-to-rank can be prohibitively expensive and challenging. In this work, we show that grayscale data can be automatically constructed without human effort. Our method employs off-the-shelf response retrieval models and response generation models as automatic grayscale data generators. With the constructed grayscale data, we propose multi-level ranking objectives for training, which can (1) teach a matching model to capture more fine-grained context-response relevance difference and (2) reduce the train-test discrepancy in terms of distractor strength. Our method is simple, effective, and universal. Experiments on three benchmark datasets and four state-of-the-art matching models show that the proposed approach brings significant and consistent performance improvements.- Anthology ID:
- 2020.emnlp-main.741
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9220–9229
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.741
- DOI:
- 10.18653/v1/2020.emnlp-main.741
- Cite (ACL):
- Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu, Haitao Zheng, and Shuming Shi. 2020. The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9220–9229, Online. Association for Computational Linguistics.
- Cite (Informal):
- The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection (Lin et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.emnlp-main.741.pdf
- Data
- Douban, E-commerce