# Dynamic Multi-Level Multi-Task Learning for Sentence Simplification

arXiv: https://arxiv.org/abs/1806.07304 · HTML: https://mlsanity.com/paper/1806.07304/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2018.

## Built on by (most cited first, 25 of 25)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [Evaluating Factuality in Text Simplification](https://mlsanity.com/paper/2204.07562/) (2022)
- [Text Simplification by Tagging](https://mlsanity.com/paper/2103.05070/) (2021)
- [Document-Level Text Simplification: Dataset, Criteria and Baseline](https://mlsanity.com/paper/2110.05071/) (2021)
- [Improving Paraphrase Detection with the Adversarial Paraphrasing Task](https://mlsanity.com/paper/2106.07691/) (2021)
- [Multitasking Framework for Unsupervised Simple Definition Generation](https://mlsanity.com/paper/2203.12926/) (2022)
- [Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data](https://mlsanity.com/paper/2302.00674/) (2023)
- [Learning to Paraphrase Sentences to Different Complexity Levels](https://mlsanity.com/paper/2308.02226/) (2023)
- [The SAMER Arabic Text Simplification Corpus](https://mlsanity.com/paper/2404.18615/) (2024)
- [GRS: Combining Generation and Revision in Unsupervised Sentence Simplification](https://mlsanity.com/paper/2203.09742/) (2022)
- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [Investigating Text Simplification Evaluation](https://mlsanity.com/paper/2107.13662/) (2021)
- [Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation](https://mlsanity.com/paper/2404.03278/) (2024)
- [Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs](https://mlsanity.com/paper/2408.04217/) (2024)
- [Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems](https://mlsanity.com/paper/2104.04000/) (2021)
- [MUSER: MUltimodal Stress Detection using Emotion Recognition as an Auxiliary Task](https://mlsanity.com/paper/2105.08146/) (2021)
- [(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification](https://mlsanity.com/paper/2212.09848/) (2022)
- [SiTSE: Sinhala Text Simplification Dataset and Evaluation](https://mlsanity.com/paper/2412.01293/) (2024)
- [Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition](https://mlsanity.com/paper/2502.11457/) (2025)
- [Unsupervised Sentence Simplification via Dependency Parsing](https://mlsanity.com/paper/2206.12261/) (2022)
- [Mitigating Data Scarcity for Large Language Models](https://mlsanity.com/paper/2302.01806/) (2023)
- [Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans](https://mlsanity.com/paper/2303.05126/) (2023)
- [Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation](https://mlsanity.com/paper/2301.02275/) (2023)

## Abstract (arXiv)

Sentence simplification aims to improve readability and understandability, based on several operations such as splitting, deletion, and paraphrasing. However, a valid simplified sentence should also be logically entailed by its input sentence. In this work, we first present a strong pointer-copy mechanism based sequence-to-sequence sentence simplification model, and then improve its entailment and paraphrasing capabilities via multi-task learning with related auxiliary tasks of entailment and paraphrase generation. Moreover, we propose a novel 'multi-level' layered soft sharing approach where each auxiliary task shares different (higher versus lower) level layers of the sentence simplification model, depending on the task's semantic versus lexico-syntactic nature. We also introduce a novel multi-armed bandit based training approach that dynamically learns how to effectively switch across tasks during multi-task learning. Experiments on multiple popular datasets demonstrate that our model outperforms competitive simplification systems in SARI and FKGL automatic metrics, and human evaluation. Further, we present several ablation analyses on alternative layer sharing methods, soft versus hard sharing, dynamic multi-armed bandit sampling approaches, and our model's learned entailment and paraphrasing skills.