Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages

TL;DR

This paper introduces a joint Transformer/RNN model for gesture typing in Indic languages, supporting native and transliterated input, with datasets and a decoding approach that improves accuracy over previous methods.

Contribution

The paper presents a novel joint Transformer/RNN architecture for gesture typing in Indic languages, handling native and transliterated input without co-character independence assumptions.

Findings

Model achieves 70-95% accuracy across 7 languages.

Created and released datasets of keyboard traces and transliteration pairs.

Outperforms prior approaches in gesture decoding and transliteration tasks.

Abstract

Gesture typing is a method of typing words on a touch-based keyboard by creating a continuous trace passing through the relevant keys. This work is aimed at developing a keyboard that supports gesture typing in Indic languages. We begin by noting that when dealing with Indic languages, one needs to cater to two different sets of users: (i) users who prefer to type in the native Indic script (Devanagari, Bengali, etc.) and (ii) users who prefer to type in the English script but want the output transliterated into the native script. In both cases, we need a model that takes a trace as input and maps it to the intended word. To enable the development of these models, we create and release two datasets. First, we create a dataset containing keyboard traces for 193,658 words from 7 Indic languages. Second, we curate 104,412 English-Indic transliteration pairs from Wikidata across these languages. Using these datasets we build a model that performs path decoding, transliteration, and transliteration correction. Unlike prior approaches, our proposed model does not make co-character independence assumptions during decoding. The overall accuracy of our model across the 7 languages varies from 70-95%.