Handling Compounding in Mobile Keyboard Input

TL;DR

This paper introduces a framework using binding types and subword units to improve mobile keyboard input in morphologically rich languages, significantly reducing word error rates.

Contribution

The paper presents a novel approach with binding types and subword units to handle compounding in languages, achieving substantial error rate reductions.

Findings

Approximately 20% word error rate reduction across languages

More than double the improvement over previous basic methods

Effective handling of compounding in morphologically rich languages

Abstract

This paper proposes a framework to improve the typing experience of mobile users in morphologically rich languages. Smartphone keyboards typically support features such as input decoding, corrections and predictions that all rely on language models. For latency reasons, these operations happen on device, so the models are of limited size and cannot easily cover all the words needed by users for their daily tasks, especially in morphologically rich languages. In particular, the compounding nature of Germanic languages makes their vocabulary virtually infinite. Similarly, heavily inflecting and agglutinative languages (e.g. Slavic, Turkic or Finno-Ugric languages) tend to have much larger vocabularies than morphologically simpler languages, such as English or Mandarin. We propose to model such languages with automatically selected subword units annotated with what we call binding types, allowing the decoder to know when to bind subword units into words. We show that this method brings around 20% word error rate reduction in a variety of compounding languages. This is more than twice the improvement we previously obtained with a more basic approach, also described in the paper.