Chinese Pinyin Aided IME, Input What You Have Not Keystroked Yet

TL;DR

This paper introduces a neural sequence-to-sequence model with gated attention for Chinese pinyin IMEs, enabling prediction of characters with incomplete input by leveraging multi-turn context, thus improving user experience.

Contribution

It presents the first neural P2C model for Chinese IMEs that utilizes multi-turn context, advancing input prediction beyond traditional methods.

Findings

Significant improvement in user experience over traditional models

Effective encoding of multi-turn context for incomplete pinyin input

First engineering implementation of a neural Chinese IME

Abstract

Chinese pinyin input method engine (IME) converts pinyin into character so that Chinese characters can be conveniently inputted into computer through common keyboard. IMEs work relying on its core component, pinyin-to-character conversion (P2C). Usually Chinese IMEs simply predict a list of character sequences for user choice only according to user pinyin input at each turn. However, Chinese inputting is a multi-turn online procedure, which can be supposed to be exploited for further user experience promoting. This paper thus for the first time introduces a sequence-to-sequence model with gated-attention mechanism for the core task in IMEs. The proposed neural P2C model is learned by encoding previous input utterance as extra context to enable our IME capable of predicting character sequence with incomplete pinyin input. Our model is evaluated in different benchmark datasets showing great user experience improvement compared to traditional models, which demonstrates the first engineering practice of building Chinese aided IME.