文本中语义信息的几何轮廓:帧条件唯一性与标量摘要的权衡三角形
A Geometric Profile of Semantic Information in Text: Frame-Conditional Uniqueness and a Trade-Off Triangle for Scalar Summaries
AI总结:
提出一个几何框架,通过句子嵌入的结构测量文本语义内容,包括三个坐标(新颖性、广度、整合性),并证明任何标量摘要都无法同时满足分析稳定性、序数鲁棒性和跨表示可比性。
摘要:
一段文本承载了多少意义?香农的理论衡量符号上的不确定性,并有意忽略意义,而诸如BERTScore的成对度量比较两段文本而非表征单段文本。我们开发了一个几何框架,从文本句子嵌入的结构中测量语义内容。该框架包含三个部分。首先,在固定的嵌入和基线内,六个自然公理唯一确定一个标量度量(尺度可调),即帧条件唯一性定理。得到的标量在经验上过于粗糙,这促使我们寻求更丰富的表征。其次,我们提出一个三坐标语义轮廓,捕捉新颖性(与通用话语的偏离)、广度(不同思想的多样性)和整合性(它们之间的连通性),以及一个离散的最小单元(语义量子),其分辨率由聚类阈值$\tau$固定。第三,我们证明了一个不可能定理:轮廓的任何标量摘要都不能同时满足在释义和拼接下的分析稳定性、跨文本尺度的序数鲁棒性以及跨表征的可比性。我们展示了两个实用标量$S_{\mathrm{minmax}}$和$S_{\mathrm{rank}}$,每个占据这个权衡三角形的不同角落。在23个合成类别、5本Project Gutenberg小说和3个嵌入模型上的验证确认了该权衡。推荐的秩归一化配置在28个序数检验中通过25个(Benjamini-Hochberg校正后通过21个),优于包括单字熵和基于BERTScore的新颖性信号在内的七个基线。一个独立的变分结果将广度坐标与行列式点过程的对数行列式联系起来(在507个Gutenberg章节上Spearman $\rho = 0.985$),为广度提供了优化理论基础。
英文摘要:
How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metrics such as BERTScore compare two texts rather than characterizing one. We develop a geometric framework that measures semantic content from the structure of a text's sentence embeddings. The framework has three parts. First, within a fixed embedding and baseline, six natural axioms uniquely determine a scalar measure up to scale, a frame-conditional uniqueness theorem. The resulting scalar is empirically too coarse, motivating a richer representation. Second, we propose a three-coordinate semantic profile capturing novelty (displacement from generic discourse), breadth (diversity of distinct ideas), and integration (connectedness among them), together with a discrete minimal unit (the semantic quantum) whose resolution is fixed by a clustering threshold $τ$. Third, we prove a no-go theorem: no scalar summary of the profile can simultaneously satisfy analytic stability under paraphrase and concatenation, ordinal robustness across text scales, and cross-representation comparability. We exhibit two practical scalars, $S_{\mathrm{minmax}}$ and $S_{\mathrm{rank}}$, each occupying a distinct corner of this trade-off triangle. Validation across 23 synthetic categories, 5 Project Gutenberg novels, and 3 embedding models confirms the trade-off. The recommended rank-normalized configuration passes 25 of 28 ordinal checks as point estimates (21 of 28 after Benjamini-Hochberg correction), outperforming seven baselines including unigram entropy and a BERTScore-based novelty signal. A separate variational result connects the breadth coordinate to the log-determinant of a determinantal point process (Spearman $ρ= 0.985$ over 507 Gutenberg chapters), giving an optimization-theoretic foundation for breadth.
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。