标题： PKAG-DDI：用于药物-药物相互作用事件文本生成的成对知识增强语言模型 显示英文标题

标题： PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text Generation

摘要： 药物-药物相互作用（DDIs）发生在多种药物同时给药时。准确预测DDIs的特定机制（称为DDI事件或DDIEs）对于药物的安全临床使用至关重要。DDIEs通常以文本描述的形式表示。然而，大多数计算方法更关注于预测DDIE类别标签，而不是生成人类可读的自然语言，这增加了临床医生的解释成本。此外，当前的方法忽略了在DDI中每种药物具有不同的生物功能这一事实，当作为输入上下文使用时，可以增强对DDIE过程的理解，并通过语言模型（LM）促进DDIE生成。在本工作中，我们提出了一种新颖的成对知识增强生成方法（称为PKAG-DDI）用于DDIE文本生成。它包括一个成对知识选择器，能够双向且同时有效地注入药物之间的结构信息，从知识集中选择成对的生物功能，以及一个成对知识集成策略，将选定的生物功能进行匹配并整合到语言模型中。在两个专业数据集上的实验表明，PKAG-DDI在DDIE文本生成方面优于现有方法，特别是在具有挑战性的归纳场景中，表明其实用性和泛化能力。 显示英文摘要

摘要： Drug-drug interactions (DDIs) arise when multiple drugs are administered concurrently. Accurately predicting the specific mechanisms underlying DDIs (named DDI events or DDIEs) is critical for the safe clinical use of drugs. DDIEs are typically represented as textual descriptions. However, most computational methods focus more on predicting the DDIE class label over generating human-readable natural language increasing clinicians' interpretation costs. Furthermore, current methods overlook the fact that each drug assumes distinct biological functions in a DDI, which, when used as input context, can enhance the understanding of the DDIE process and benefit DDIE generation by the language model (LM). In this work, we propose a novel pairwise knowledge-augmented generative method (termed PKAG-DDI) for DDIE text generation. It consists of a pairwise knowledge selector efficiently injecting structural information between drugs bidirectionally and simultaneously to select pairwise biological functions from the knowledge set, and a pairwise knowledge integration strategy that matches and integrates the selected biological functions into the LM. Experiments on two professional datasets show that PKAG-DDI outperforms existing methods in DDIE text generation, especially in challenging inductive scenarios, indicating its practicality and generalization.