Recurrent Inference in Text Editing
This addresses text editing inefficiencies for NLP applications, but it is incremental as it builds on existing sequence-to-sequence approaches.
The paper tackles the problem of performance degradation in neural text editing due to limited source text encoding and long decoding steps by proposing Recurrence, an iterative inference method that narrows the problem space, achieving improvements on arithmetic text editing tasks.
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.