Logo image
Back
Clustering and Network Analysis for the Embedding Spaces of Sentences and Sub-Sentences
Conference proceeding   Open access

Clustering and Network Analysis for the Embedding Spaces of Sentences and Sub-Sentences

Yuan An, Alexander Kalinowski and Jane Greenberg
2021 Second International Conference on Intelligent Data Science Technologies and Applications (IDSTA)
15 Nov 2021
DOI: https://doi.org/10.1109/IDSTA53674.2021.9660801
url
https://arxiv.org/pdf/2110.00697View
SubmittedarXiv.org - Non-exclusive license to distribute,  Open

Abstract

Clustering Analysis Data science Embedding Space Analysis Natural language processing Network Analysis Network analyzers Network topology Sentence Embedding Topology
Sentence embedding methods offer a powerful approach for working with short textual constructs or sequences of words. By representing sentences as dense numerical vectors, many natural language processing (NLP) applications have improved their performance. However, relatively little is understood about the latent structure of sentence embeddings. Specifically, research has not addressed whether the length and structure of sentences impact the sentence embedding space and topology. This paper reports research on a set of comprehensive clustering and network analyses targeting sentence and sub-sentence embedding spaces. Results show that one method generates the most clusterable embeddings. In general, the embeddings of span sub-sentences have better clustering properties than the original sentences. The results have implications for future sentence embedding models and applications.

Metrics

17 Record Views
2 citations in Web of Science
1 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Information Systems
Logo image