CLAILGMay 11, 2020

Enabling Language Models to Fill in the Blanks

arXiv:2005.05339v21051 citations
AI Analysis

This enables richer functionality for writing assistance tools by generalizing language models beyond end-of-document prediction.

The paper tackles the problem of text infilling, extending language models to predict missing spans at any position in documents, and shows that their approach effectively infills entire sentences across domains like short stories, scientific abstracts, and lyrics, with humans struggling to detect machine-generated infills in short stories.

We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While infilling could enable rich functionality especially for writing assistance tools, more attention has been devoted to language modeling---a special case of infilling where text is predicted at the end of a document. In this paper, we aim to extend the capabilities of language models (LMs) to the more general task of infilling. To this end, we train (or fine-tune) off-the-shelf LMs on sequences containing the concatenation of artificially-masked text and the text which was masked. We show that this approach, which we call infilling by language modeling, can enable LMs to infill entire sentences effectively on three different domains: short stories, scientific abstracts, and lyrics. Furthermore, we show that humans have difficulty identifying sentences infilled by our approach as machine-generated in the domain of short stories.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes