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 $\lambda$ in token-level loss weights can be used to control the edit distance and the simplicity level (FKGL).

翻译：自动简化可帮助非专业人士理解复杂的科学文本。语言模型常通过将复杂语言翻译为简单语言来应用于此任务。本文基于Llama 2构建系统，该模型在针对生物医学文本简化的PLABA共享任务中排名第一。我们发现输入与输出间大量共享词元导致训练信号微弱且模型编辑趋于保守。为缓解此问题，我们提出句子级和词元级损失权重：前者对编辑距离标注的修改词元赋予更高权重，后者则基于编辑操作。在PLABA数据集上的实证评估表明，与以标准交叉熵微调的相同模型相比，两种方法生成的简化文本更接近人工标注结果（SARI值提升+1.8%/+3.5%），语言更简单（FKGL降低-1/-1.1），编辑量更大（编辑距离提升1.6倍/1.8倍）。我们进一步证明，词元级损失权重中的超参数λ可有效控制编辑距离与简化程度（FKGL）。