Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.00500 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910783263211520 |
|---|---|
| author | Draganov, Ondřej Skiena, Steven |
| author_facet | Draganov, Ondřej Skiena, Steven |
| contents | Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the notion of persistent homology from topological data analysis (TDA) to measure the distances between language pairs from the shape of their unlabeled embeddings. These distances quantify the degree of non-isometry of the embeddings. To distinguish whether these differences are random training errors or capture real information about the languages, we use the computed distance matrices to construct language phylogenetic trees over 81 Indo-European languages. Careful evaluation shows that our reconstructed trees exhibit strong and statistically-significant similarities to the reference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00500 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysis Draganov, Ondřej Skiena, Steven Computation and Language Algebraic Topology Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the notion of persistent homology from topological data analysis (TDA) to measure the distances between language pairs from the shape of their unlabeled embeddings. These distances quantify the degree of non-isometry of the embeddings. To distinguish whether these differences are random training errors or capture real information about the languages, we use the computed distance matrices to construct language phylogenetic trees over 81 Indo-European languages. Careful evaluation shows that our reconstructed trees exhibit strong and statistically-significant similarities to the reference. |
| title | The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysis |
| topic | Computation and Language Algebraic Topology |
| url | https://arxiv.org/abs/2404.00500 |