# BoschAI @ PLABA 2023: Leveraging Edit Operations in End-to-End Neural Sentence Simplification

arXiv: https://arxiv.org/abs/2311.01907 · HTML: https://mlsanity.com/paper/2311.01907/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing](https://mlsanity.com/paper/1906.08104/) (2019)
- [Iterative Edit-Based Unsupervised Sentence Simplification](https://mlsanity.com/paper/2006.09639/) (2020)
- [EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints](https://mlsanity.com/paper/2011.06868/) (2020)
- [Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification](https://mlsanity.com/paper/1904.02767/) (2019)
- [A Dataset for Plain Language Adaptation of Biomedical Abstracts](https://mlsanity.com/paper/2210.12242/) (2022)

## Built on by (most cited first, 1 of 1)

- [Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation](https://mlsanity.com/paper/2609.17398/) (2026)

## Abstract (arXiv)

Automatic simplification can help laypeople to comprehend complex scientific text. Language models are frequently applied to this task by translating from complex to simple language. In this paper, we describe our system based on Llama 2, which ranked first in the PLABA shared task addressing the simplification of biomedical text. We find that the large portion of shared tokens between input and output leads to weak training signals and conservatively editing models. To mitigate these issues, we propose sentence-level and token-level loss weights. They give higher weight to modified tokens, indicated by edit distance and edit operations, respectively. We conduct an empirical evaluation on the PLABA dataset and find that both approaches lead to simplifications closer to those created by human annotators (+1.8% / +3.5% SARI), simpler language (-1 / -1.1 FKGL) and more edits (1.6x / 1.8x edit distance) compared to the same model fine-tuned with standard cross entropy. We furthermore show that the hyperparameter λ in token-level loss weights can be used to control the edit distance and the simplicity level (FKGL).