QuickEdit: Editing Text & Translations by Crossing Words Out

TL;DR

QuickEdit introduces a neural framework for text editing that allows users to mark words for change, enabling efficient translation post-editing and paraphrasing through simple interactions and neural sequence-to-sequence models.

Contribution

It presents a novel neural editing model that reformulates sentences based on user-marked tokens, trained on translation data to improve post-editing and paraphrasing tasks.

Findings

Effective in translation post-editing scenarios.

User study shows improved paraphrasing quality.

Outperforms baseline methods in simulated edits.

Abstract

We propose a framework for computer-assisted text editing. It applies to translation post-editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor modifies a sentence by marking tokens they would like the system to change. Our model then generates a new sentence which reformulates the initial sentence by avoiding marked words. The approach builds upon neural sequence-to-sequence modeling and introduces a neural network which takes as input a sentence along with change markers. Our model is trained on translation bitext by simulating post-edits. We demonstrate the advantage of our approach for translation post-editing through simulated post-edits. We also evaluate our model for paraphrasing through a user study.