个性化术语识别以增强跨学科交流
Personalized Jargon Identification for Enhanced Interdisciplinary Communication
AI总结：
针对跨学科交流中术语熟悉度因人而异的问题，收集11位研究者的10K+标注数据，提出结合个人出版物的提示方法预测个体术语熟悉度，实现个性化术语识别。
摘要：
科学术语可能会阻碍研究人员阅读其他领域的材料。当前的术语识别方法主要使用语料库级别的熟悉度指标（例如，简单维基百科代表通俗语言）。然而，研究人员对术语的熟悉程度可能因其自身背景而有很大差异。我们收集了一个数据集，包含来自11位计算机科学研究人员的超过10K条术语熟悉度标注，这些术语取自100篇论文摘要。对此数据的分析显示，即使在同一子领域（如NLP）内，术语熟悉度和信息需求在不同标注者之间也存在很大差异。我们研究了代表个人、子领域和领域知识的特征，以预测个人的术语熟悉度。我们比较了监督式和基于提示的方法，发现包括个人出版物的基于提示的方法取得了最高的准确率，尽管零样本提示提供了一个强大的基线。这项研究为将个人数据整合到科学术语识别中提供了关于特征和方法的见解。
英文摘要：
Scientific jargon can impede researchers when they read materials from other domains. Current methods of jargon identification mainly use corpus-level familiarity indicators (e.g., Simple Wikipedia represents plain language). However, researchers' familiarity of a term can vary greatly based on their own background. We collect a dataset of over 10K term familiarity annotations from 11 computer science researchers for terms drawn from 100 paper abstracts. Analysis of this data reveals that jargon familiarity and information needs vary widely across annotators, even within the same sub-domain (e.g., NLP). We investigate features representing individual, sub-domain, and domain knowledge to predict individual jargon familiarity. We compare supervised and prompt-based approaches, finding that prompt-based methods including personal publications yields the highest accuracy, though zero-shot prompting provides a strong baseline. This research offers insight into features and methods to integrate personal data into scientific jargon identification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
