Text Editing by Command

TL;DR

This paper introduces an interactive text editing framework that allows users to modify generated text through commands, addressing limitations of one-shot generation especially for longer, dynamic documents.

Contribution

It proposes a new text editing task, creates the WikiDocEdits dataset, and develops an Interactive Editor model that outperforms baselines in both automatic and human evaluations.

Findings

The Interactive Editor outperforms baseline models.

The dataset enables training models for dynamic text editing.

Positive results in both automatic and human evaluations.

Abstract

A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step. The one-shot setting is inadequate, however, when the constraints the user wishes to impose on the generated text are dynamic, especially when authoring longer documents. We address this limitation with an interactive text generation setting in which the user interacts with the system by issuing commands to edit existing text. To this end, we propose a novel text editing task, and introduce WikiDocEdits, a dataset of single-sentence edits crawled from Wikipedia. We show that our Interactive Editor, a transformer-based model trained on this dataset, outperforms baselines and obtains positive results in both automatic and human evaluations. We present empirical and qualitative analyses of this model's performance.