Fast Word Predictor for On-Device Application

Huy Tien Nguyen, Khoi Tuan Nguyen, Anh Tuan Nguyen, Thanh Lac Thi Tran


Abstract
Learning on large text corpora, deep neural networks achieve promising results in the next word prediction task. However, deploying these huge models on devices has to deal with constraints of low latency and a small binary size. To address these challenges, we propose a fast word predictor performing efficiently on mobile devices. Compared with a standard neural network which has a similar word prediction rate, the proposed model obtains 60% reduction in memory size and 100X faster inference time on a middle-end mobile device. The method is developed as a feature for a chat application which serves more than 100 million users.
Anthology ID:
2020.coling-demos.5
Volume:
Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Michal Ptaszynski, Bartosz Ziolko
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics (ICCL)
Note:
Pages:
23–27
Language:
URL:
https://aclanthology.org/2020.coling-demos.5
DOI:
10.18653/v1/2020.coling-demos.5
Bibkey:
Cite (ACL):
Huy Tien Nguyen, Khoi Tuan Nguyen, Anh Tuan Nguyen, and Thanh Lac Thi Tran. 2020. Fast Word Predictor for On-Device Application. In Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations, pages 23–27, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
Cite (Informal):
Fast Word Predictor for On-Device Application (Nguyen et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-demos.5.pdf