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.- Anthology ID:
- 2020.findings-emnlp.159
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1758–1769
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.159
- DOI:
- 10.18653/v1/2020.findings-emnlp.159
- Cite (ACL):
- Ning Shi, Ziheng Zeng, Haotian Zhang, and Yichen Gong. 2020. Recurrent Inference in Text Editing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1758–1769, Online. Association for Computational Linguistics.
- Cite (Informal):
- Recurrent Inference in Text Editing (Shi et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.159.pdf
- Code
- ShiningLab/Recurrent-Text-Editing