Recurrent Inference in Text Editing

TL;DR

This paper introduces Recurrence, a novel iterative inference method for neural text editing that improves performance by progressively applying short editing actions, addressing limitations of traditional sequence-to-sequence approaches.

Contribution

The paper proposes Recurrence, an iterative inference framework for text editing that narrows the problem space and enhances editing accuracy over existing methods.

Findings

Recurrence outperforms conventional inference methods on three text editing tasks.

The method effectively handles varying difficulty levels in editing tasks.

Iterative editing reduces errors caused by limited source encoding.

Abstract

In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long, varying decoding steps. To address this problem, we propose a new inference method, Recurrence, that iteratively performs editing actions, significantly narrowing the problem space. In each iteration, encoding the partially edited text, Recurrence decodes the latent representation, generates an action of short, fixed-length, and applies the action to complete a single edit. For a comprehensive comparison, we introduce three types of text editing tasks: Arithmetic Operators Restoration (AOR), Arithmetic Equation Simplification (AES), Arithmetic Equation Correction (AEC). Extensive experiments on these tasks with varying difficulties demonstrate that Recurrence achieves improvements over conventional inference methods.