Kenneth Arnold, Kai-Wei Chang, Adam T. Kalai




We study the challenge of suggesting multi-word phrases to be inserted while typing on a mobile keyboard. Recent work in mobile text entry user-interfaces has shown that, unlike single-word predictions, these phrases are treated as suggestions rather than predictions, meaning that users often insert words that weren't what they were planning on typing.
This suggests the NLP problem of offering multi-word suggestions that are likely to be accepted by a user. We propose a method for customizing an existing language model to adapt it to a specific such task, and show how to learn the parameters of that customization offline.


A short version was presented at AAAI Workshop on Human-Aware Artificial Intelligence"

Bib entry

author = {Kenneth Arnold and Kai-Wei Chang and Adam T. Kalai},
title = {Counterfactual Language Model Adaptation for Suggesting Phrases},
booktitle = {IJCNLP},
year = {2017},