Enabling Real-time Neural IME with Incremental Vocabulary Selection

Jiali Yao, Raphael Shu, Xinjian Li, Katsutoshi Ohtsuki, Hideki Nakayama


Abstract
Input method editor (IME) converts sequential alphabet key inputs to words in a target language. It is an indispensable service for billions of Asian users. Although the neural-based language model is extensively studied and shows promising results in sequence-to-sequence tasks, applying a neural-based language model to IME was not considered feasible due to high latency when converting words on user devices. In this work, we articulate the bottleneck of neural IME decoding to be the heavy softmax computation over a large vocabulary. We propose an approach that incrementally builds a subset vocabulary from the word lattice. Our approach always computes the probability with a selected subset vocabulary. When the selected vocabulary is updated, the stale probabilities in previous steps are fixed by recomputing the missing logits. The experiments on Japanese IME benchmark shows an over 50x speedup for the softmax computations comparing to the baseline, reaching real-time speed even on commodity CPU without losing conversion accuracy. The approach is potentially applicable to other incremental sequence-to-sequence decoding tasks such as real-time continuous speech recognition.
Anthology ID:
N19-2001
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Anastassia Loukina, Michelle Morales, Rohit Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–8
Language:
URL:
https://aclanthology.org/N19-2001
DOI:
10.18653/v1/N19-2001
Bibkey:
Cite (ACL):
Jiali Yao, Raphael Shu, Xinjian Li, Katsutoshi Ohtsuki, and Hideki Nakayama. 2019. Enabling Real-time Neural IME with Incremental Vocabulary Selection. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 1–8, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Enabling Real-time Neural IME with Incremental Vocabulary Selection (Yao et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-2001.pdf
Code
 jiali-ms/JLM