Real-Time Optimized N-gram For Mobile Devices

TL;DR

This paper introduces Op-Ngram, a lightweight N-gram language model optimized for mobile devices, significantly reducing size and loading time while improving word prediction performance across various phone types.

Contribution

The paper presents a novel end-to-end N-gram pipeline, Op-Ngram, that efficiently utilizes mobile resources for faster and more compact language modeling on low-end and high-end devices.

Findings

37% reduction in LM-ROM size

76% reduction in LM-RAM size

88% faster loading time

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.