arXiv cs.CL· Elif Dorukba\c{s}{\i}, \.Ilker T\"urker·· 23 小时前AI 评分18
用可见图表示词嵌入做文本分类
Visibility Graph Representations of Word Embeddings for Text Classification
AI 导读
研究将词嵌入平均为定长文档向量后转为自然可见图,以节点度数向量或邻接矩阵输入分类器做新闻主题分类。在 AG News 四分类基准上,卡方筛选保留 100 至 1,500 词,度数表示在 1,000 词时达到最高 91.24% 准确率,1,500 词时比 BERT 基线高 0.29 个百分点;卷积对比中邻接矩阵输入在 1,000 词时达 86.16%,高于最强静态嵌入的 83.12%。
正文 · 原文
Abstract:Text classifiers depend on representations that expose the distinctions between classes in a form the learning model can use, and a restricted vocabulary changes which representation is most effective. This paper studies natural visibility graphs as an intermediate representation for news topic classification under controlled vocabulary budgets. Word embeddings are averaged into a fixed-length document vector, the vector is read as an ordered numerical series, and its natural visibility graph is passed to a classifier either as an ordered node-degree vector or as an adjacency matrix. On the four-class AG News benchmark, chi-square selection retains 100 to 1,500 words, and the graph inputs are compared with direct embedding-based representations from continuous bag-of-words, skip-gram, GloVe, FastText and BERT. With a fully connected classifier, the degree representation is the most accurate configuration from 700 selected words onward; it reaches its highest accuracy of 91.24% at 1,000 words and exceeds the BERT-based baseline by 0.29 percentage points at 1,500 words. In a separate convolutional comparison, the adjacency input reaches 86.16% at 1,000 words, against 83.12% for the strongest static embedding. The results indicate that visibility-derived features can be competitive once the selected vocabulary provides adequate coverage. We discuss the roles of graph compression, coordinate ordering and classifier choice, and the controls needed to establish the reliability of the small differences observed.
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7; I.5.4 |
| Cite as: | arXiv:2611.22685 [cs.CL] |
| (or arXiv:2611.22685v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22685 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elif Dorukbaşı [view email]
[v1]
Tue, 17 Nov 2026 12:35:55 UTC (1,026 KB)
来源:arXiv cs.CL · arxiv.org