超越频率度量：上下文嵌入能否捕捉科学文本中的意义变化？
Beyond frequency measures: Can contextual embeddings capture meaning change in scientific texts?
浏览论文内容
中文总结 AI 辅助
本研究比较频率与上下文嵌入方法在科学文本中捕捉术语意义变化的能力，发现频率方法略优但嵌入指标能识别关键概念发展，建议整合两者以增强趋势分析。
中文摘要 AI 辅助
识别技术趋势是科学计量学的核心任务，然而传统的基于频率的方法难以捕捉领域特定术语的实质性意义转变。我们假设上下文嵌入可以补充频率动态，以有效追踪历时语义变化。我们在2010年至2024年的天体物理学和自然语言处理语料库中比较了基于频率和基于嵌入的方法。使用KeyBERT（以其底层语言模型SciBERT为基础）提取候选术语，并通过Fisher精确检验筛选出频率显著增加的术语。随后，领域专家对这些术语进行真正的语义转变评估，以建立真实标签。为了量化语义漂移，我们使用多种指标比较两个离散时期中每个术语的上下文嵌入“云”：余弦距离、平均成对距离、Hotelling型T2和最大均值差异。结果表明，基于频率的方法与人类对“趋势相关术语”的判断略优于语义指标（在天体物理学中Precision@50为0.62对0.60）。两种信号的相关性约为0.6。仅由嵌入指标识别出的几个术语（例如“原初黑洞”）代表了纯频率分析无法察觉的关键概念发展。这些发现表明，语义指标可能捕获互补信息，凸显了将上下文嵌入整合到科学计量趋势分析中的价值。
英文摘要
Identifying technological trends is a core scientometric task, yet traditional frequency-based approaches struggle to capture substantial meaning shifts of domain-specific terms. We hypothesise that contextual embeddings can complement frequency dynamics to effectively track diachronic semantic change. We compare frequency and embedding-based approaches across Astrophysics and NLP corpora spanning from 2010 to 2024. Candidate terms are extracted using KeyBERT (utilizing SciBERT as its underlying language model) and filtered for significant frequency increases using Fisher's exact test. These terms are then evaluated for genuine semantic shift by domain experts to establish ground-truth labels. To quantify semantic drift, each term's contextual embedding ''clouds'' from the two discrete periods are compared using multiple metrics: cosine distance, average pairwise distance, Hotelling-type T 2 , and maximum mean discrepancy. Results indicate that frequency-based methods align slightly better with human judgments of ''trend-related terms'' than semantic metrics (Precision@50 of 0.62 vs 0.60 in Astrophysics). The two signals show a correlation of around 0.6. Several terms identified exclusively by embedding metrics (e.g., ''primordial black holes'') represent critical conceptual developments invisible to pure frequency analysis. These findings indicate that semantic metrics may capture complementary information, highlighting the value of integrating contextual embeddings into scientometric trend analysis.
发表机构
- Université Paris-Saclay（巴黎-萨克雷大学）
- Université de Strasbourg（斯特拉斯堡大学）
机构由 AI 辅助整理，请以论文原文为准。
