2019/01/01 by Sharmila Mani, Sourabh Vasant Gothe, Sourav Ghosh +5 · 1 citation
Computer Science · Mathematics · #Computer science #Feature (linguistics) #Language model #Mathematics #Mobile device #Mobile radio #Mobile telephony #Natural Language Processing Techniques #Operating system #Pipeline (software) #Programming language #Pruning #Real-time computing #Speech Recognition and Synthesis #Speech recognition #Telecommunications #Topic Modeling #Word (group theory) #cs.CL #n-gram
paper · pdf · doi:10.1109/icosc.2019.8665639
published as 2019 IEEE 13th International Conference on Semantic Computing (ICSC), Newport Beach, CA, USA, 2019, pp. 87-92 · 2019 IEEE 13th International Conference on Semantic Computing (ICSC). Accessible at https://ieeexplore.ieee.org/document/8665639
openalex publication_date 2019/01/01 · arxiv created 2021/01/07 · arxiv updated 2021/01/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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 [1] 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[2]. Moreover, our method shows significant performance improvement over KenLM[3] as well.