# Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification

arXiv: https://arxiv.org/abs/1904.02767 · HTML: https://mlsanity.com/paper/1904.02767/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 20 of 20)

- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Paragraph-level Simplification of Medical Texts](https://mlsanity.com/paper/2104.05767/) (2021)
- [CoditT5: Pretraining for Source Code and Natural Language Editing](https://mlsanity.com/paper/2208.05446/) (2022)
- [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)
- [Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing](https://mlsanity.com/paper/2112.06924/) (2021)
- [Measuring and Reducing Model Update Regression in Structured Prediction for NLP](https://mlsanity.com/paper/2202.02976/) (2022)
- [Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2401.05054/) (2024)
- [How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks](https://mlsanity.com/paper/2109.04604/) (2021)
- [GRS: Combining Generation and Revision in Unsupervised Sentence Simplification](https://mlsanity.com/paper/2203.09742/) (2022)
- [An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment](https://mlsanity.com/paper/2403.04963/) (2024)
- [Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding](https://mlsanity.com/paper/2310.11191/) (2023)
- [SiTSE: Sinhala Text Simplification Dataset and Evaluation](https://mlsanity.com/paper/2412.01293/) (2024)
- [Text Simplification of College Admissions Instructions: A Professionally Simplified and Verified Corpus](https://mlsanity.com/paper/2209.04529/) (2022)
- [MAViC: Multimodal Active Learning for Video Captioning](https://mlsanity.com/paper/2212.11109/) (2022)
- [BoschAI @ PLABA 2023: Leveraging Edit Operations in End-to-End Neural Sentence Simplification](https://mlsanity.com/paper/2311.01907/) (2023)
- [Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese](https://mlsanity.com/paper/2406.02974/) (2024)
- [Edit-Constrained Decoding for Sentence Simplification](https://mlsanity.com/paper/2409.19247/) (2024)
- [Can Knowledge Graphs Simplify Text?](https://mlsanity.com/paper/2308.06975/) (2023)

## Abstract (arXiv)

Sentence simplification is the task of rewriting texts so they are easier to understand. Recent research has applied sequence-to-sequence (Seq2Seq) models to this task, focusing largely on training-time improvements via reinforcement learning and memory augmentation. One of the main problems with applying generic Seq2Seq models for simplification is that these models tend to copy directly from the original sentence, resulting in outputs that are relatively long and complex. We aim to alleviate this issue through the use of two main techniques. First, we incorporate content word complexities, as predicted with a leveled word complexity model, into our loss function during training. Second, we generate a large set of diverse candidate simplifications at test time, and rerank these to promote fluency, adequacy, and simplicity. Here, we measure simplicity through a novel sentence complexity model. These extensions allow our models to perform competitively with state-of-the-art systems while generating simpler sentences. We report standard automatic and human evaluation metrics.