Improving Text Auto-Completion with Next Phrase Prediction

TL;DR

This paper introduces Next Phrase Prediction, a self-supervised training method to improve domain-specific text auto-completion by enhancing pre-trained language models, demonstrated through experiments in email and academic writing.

Contribution

Proposes a novel self-supervised Next Phrase Prediction objective to adapt language models for domain-specific auto-completion tasks efficiently.

Findings

Outperforms baseline models in email auto-completion

Enhances academic writing auto-completion accuracy

Enables faster domain adaptation of language models

Abstract

Language models such as GPT-2 have performed well on constructing syntactically sound sentences for text auto-completion task. However, such models often require considerable training effort to adapt to specific writing domains (e.g., medical). In this paper, we propose an intermediate training strategy to enhance pre-trained language models' performance in the text auto-completion task and fastly adapt them to specific domains. Our strategy includes a novel self-supervised training objective called Next Phrase Prediction (NPP), which encourages a language model to complete the partial query with enriched phrases and eventually improve the model's text auto-completion performance. Preliminary experiments have shown that our approach is able to outperform the baselines in auto-completion for email and academic writing domains.