Real-Time Optimized N-gram For Mobile Devices
Abstract
With the increasing number of mobile devices, there has been continuous research on generating optimized Language Models (LMs) for soft keyboard. In spite of advances in this domain, building a single LM for low-end feature phones as well as high-end smartphones is still a pressing need. Hence, we propose a novel technique, Optimized N-gram (Op-Ngram), an end-to-end N-gram pipeline that utilises mobile resources efficiently for faster Word Completion (WC) and Next Word Prediction (NWP). Op-Ngram applies Stupid Backoff and pruning strategies to generate a light-weight model. The LM loading time on mobile is linear with respect to model size. We observed that Op-Ngram gives 37% improvement in Language Model (LM)-ROM size, 76% in LM-RAM size, 88% in loading time and 89% in average suggestion time as compared to SORTED array variant of BerkeleyLM. Moreover, our method shows significant performance improvement over KenLM as well.
Cite
@article{arxiv.2101.03967,
title = {Real-Time Optimized N-gram For Mobile Devices},
author = {Sharmila Mani and Sourabh Vasant Gothe and Sourav Ghosh and Ajay Kumar Mishra and Prakhar Kulshreshtha and Bhargavi M and Muthu Kumaran},
journal= {arXiv preprint arXiv:2101.03967},
year = {2021}
}
Comments
2019 IEEE 13th International Conference on Semantic Computing (ICSC). Accessible at https://ieeexplore.ieee.org/document/8665639