# EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints

arXiv: https://arxiv.org/abs/2011.06868 · HTML: https://mlsanity.com/paper/2011.06868/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 24 of 24)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models](https://mlsanity.com/paper/2203.09486/) (2022)
- [User Adaptive Language Learning Chatbots with a Curriculum](https://mlsanity.com/paper/2304.05489/) (2023)
- [Nearest Neighbor Non-autoregressive Text Generation](https://mlsanity.com/paper/2208.12496/) (2022)
- [Toward Unified Controllable Text Generation via Regular Expression Instruction](https://mlsanity.com/paper/2309.10447/) (2023)
- [Integrating Translation Memories into Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2210.06020/) (2022)
- [Truveta Mapper: A Zero-shot Ontology Alignment Framework](https://mlsanity.com/paper/2301.09767/) (2023)
- [Creative Data Generation: A Review Focusing on Text and Poetry](https://mlsanity.com/paper/2305.08493/) (2023)
- [Reducing Sequence Length by Predicting Edit Operations with Large Language Models](https://mlsanity.com/paper/2305.11862/) (2023)
- [Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation](https://mlsanity.com/paper/2211.05967/) (2022)
- [Rule-based Morphological Inflection Improves Neural Terminology Translation](https://mlsanity.com/paper/2109.04620/) (2021)
- [Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints](https://mlsanity.com/paper/2204.13355/) (2022)
- [Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review](https://mlsanity.com/paper/2212.03747/) (2022)
- [Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints](https://mlsanity.com/paper/2306.12089/) (2023)
- [Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training](https://mlsanity.com/paper/2307.08416/) (2023)
- [Bilingual Synchronization: Restoring Translational Relationships with Editing Operations](https://mlsanity.com/paper/2210.13163/) (2022)
- [Interactive Text Generation](https://mlsanity.com/paper/2303.00908/) (2023)
- [Towards Example-Based NMT with Multi-Levenshtein Transformers](https://mlsanity.com/paper/2310.08967/) (2023)
- [Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation](https://mlsanity.com/paper/2109.06308/) (2021)
- [Can Multilinguality benefit Non-autoregressive Machine Translation?](https://mlsanity.com/paper/2112.08570/) (2021)
- [BoschAI @ PLABA 2023: Leveraging Edit Operations in End-to-End Neural Sentence Simplification](https://mlsanity.com/paper/2311.01907/) (2023)
- [EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification](https://mlsanity.com/paper/2606.07915/) (2026)

## Abstract (arXiv)

We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive sequence generation (Gu et al., 2019), EDITOR generates new sequences by iteratively editing hypotheses. It relies on a novel reposition operation designed to disentangle lexical choice from word positioning decisions, while enabling efficient oracles for imitation learning and parallel edits at decoding time. Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer (Gu et al., 2019) while speeding up decoding dramatically compared to constrained beam search (Post and Vilar, 2018). EDITOR also achieves comparable or better translation quality with faster decoding speed than the Levenshtein Transformer on standard Romanian-English, English-German, and English-Japanese machine translation tasks.