# Felix: Flexible Text Editing Through Tagging and Insertion

arXiv: https://arxiv.org/abs/2003.10687 · HTML: https://mlsanity.com/paper/2003.10687/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2020.

## Built on by (most cited first, 30 of 58)

- [A Simple Recipe for Multilingual Grammatical Error Correction](https://mlsanity.com/paper/2106.03830/) (2021)
- [RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs](https://mlsanity.com/paper/2305.08844/) (2023)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition](https://mlsanity.com/paper/2105.03842/) (2021)
- [On Improving Summarization Factual Consistency from Natural Language Feedback](https://mlsanity.com/paper/2212.09968/) (2022)
- [EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start](https://mlsanity.com/paper/2205.12209/) (2022)
- [Focus Attention: Promoting Faithfulness and Diversity in Summarization](https://mlsanity.com/paper/2105.11921/) (2021)
- [Learning to Model Editing Processes](https://mlsanity.com/paper/2205.12374/) (2022)
- [Text Simplification by Tagging](https://mlsanity.com/paper/2103.05070/) (2021)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation](https://mlsanity.com/paper/2305.14734/) (2023)
- [Text Generation with Text-Editing Models](https://mlsanity.com/paper/2206.07043/) (2022)
- [An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models](https://mlsanity.com/paper/2203.09486/) (2022)
- [Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks](https://mlsanity.com/paper/2212.01350/) (2022)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Assemble Foundation Models for Automatic Code Summarization](https://mlsanity.com/paper/2201.05222/) (2022)
- [Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts](https://mlsanity.com/paper/2302.09155/) (2023)
- [Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding](https://mlsanity.com/paper/2108.05064/) (2021)
- [FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction](https://mlsanity.com/paper/2210.12364/) (2022)
- [Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction](https://mlsanity.com/paper/2211.13252/) (2022)
- [ReadCtrl: Personalizing text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2406.09205/) (2024)
- [uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers](https://mlsanity.com/paper/2209.07068/) (2022)
- [Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study](https://mlsanity.com/paper/2503.00985/) (2025)
- [Non-autoregressive Text Editing with Copy-aware Latent Alignments](https://mlsanity.com/paper/2310.07821/) (2023)
- [Character Transformations for Non-Autoregressive GEC Tagging](https://mlsanity.com/paper/2111.09280/) (2021)
- [Explicit Image Caption Editing](https://mlsanity.com/paper/2207.09625/) (2022)
- [Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking](https://mlsanity.com/paper/2403.08492/) (2024)

## Abstract (arXiv)

We present Felix --- a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pre-training. In contrast to conventional sequence-to-sequence (seq2seq) models, Felix is efficient in low-resource settings and fast at inference time, while being capable of modeling flexible input-output transformations. We achieve this by decomposing the text-editing task into two sub-tasks: tagging to decide on the subset of input tokens and their order in the output text and insertion to in-fill the missing tokens in the output not present in the input. The tagging model employs a novel Pointer mechanism, while the insertion model is based on a Masked Language Model. Both of these models are chosen to be non-autoregressive to guarantee faster inference. Felix performs favourably when compared to recent text-editing methods and strong seq2seq baselines when evaluated on four NLG tasks: Sentence Fusion, Machine Translation Automatic Post-Editing, Summarization, and Text Simplification.