Text Editing by Command
This addresses the problem of dynamic text editing for users authoring longer documents, representing an incremental improvement over existing methods.
The paper tackles the limitation of one-shot text generation for dynamic constraints in longer documents by introducing an interactive text generation setting where users edit text via commands, and shows that their transformer-based Interactive Editor outperforms baselines with positive results in automatic and human evaluations.
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.