A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
Abstract
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multilingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multilingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multilingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10% on average, and 16%for low resource languages. CGM also shows remarkable improvements in diversity (80%) illustrating its expressiveness in representation of multi-lingual data.- Anthology ID:
- 2021.findings-emnlp.134
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1553–1568
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.134
- DOI:
- 10.18653/v1/2021.findings-emnlp.134
- Cite (ACL):
- Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, and Ahmed Hassan Awadallah. 2021. A Conditional Generative Matching Model for Multi-lingual Reply Suggestion. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1553–1568, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- A Conditional Generative Matching Model for Multi-lingual Reply Suggestion (Deb et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.134.pdf
- Data
- MRS