{"date_created":"2025-02-04T16:19:28Z","arxiv":1,"quality_controlled":"1","file_date_updated":"2025-02-10T08:20:34Z","OA_type":"gold","department":[{"_id":"GradSch"},{"_id":"HeEd"}],"scopus_import":"1","date_updated":"2025-02-10T08:21:37Z","OA_place":"publisher","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"citation":{"chicago":"Draganov, Ondrej, and Steven Skiena. “The Shape of Word Embeddings: Quantifying Non-Isometry with Topological Data Analysis.” In <i>Findings of the Association for Computational Linguistics: EMNLP 2024</i>, 12080–99. Association for Computational Linguistics, 2024. <a href=\"https://doi.org/10.18653/v1/2024.findings-emnlp.705\">https://doi.org/10.18653/v1/2024.findings-emnlp.705</a>.","mla":"Draganov, Ondrej, and Steven Skiena. “The Shape of Word Embeddings: Quantifying Non-Isometry with Topological Data Analysis.” <i>Findings of the Association for Computational Linguistics: EMNLP 2024</i>, Association for Computational Linguistics, 2024, pp. 12080–99, doi:<a href=\"https://doi.org/10.18653/v1/2024.findings-emnlp.705\">10.18653/v1/2024.findings-emnlp.705</a>.","ieee":"O. Draganov and S. Skiena, “The shape of word embeddings: Quantifying non-isometry with topological data analysis,” in <i>Findings of the Association for Computational Linguistics: EMNLP 2024</i>, Miami, FL, United States, 2024, pp. 12080–12099.","ama":"Draganov O, Skiena S. The shape of word embeddings: Quantifying non-isometry with topological data analysis. In: <i>Findings of the Association for Computational Linguistics: EMNLP 2024</i>. Association for Computational Linguistics; 2024:12080-12099. doi:<a href=\"https://doi.org/10.18653/v1/2024.findings-emnlp.705\">10.18653/v1/2024.findings-emnlp.705</a>","ista":"Draganov O, Skiena S. 2024. The shape of word embeddings: Quantifying non-isometry with topological data analysis. Findings of the Association for Computational Linguistics: EMNLP 2024. EMNLP: Conference on Empirical Methods in Natural Language Processing, 12080–12099.","short":"O. Draganov, S. Skiena, in:, Findings of the Association for Computational Linguistics: EMNLP 2024, Association for Computational Linguistics, 2024, pp. 12080–12099.","apa":"Draganov, O., &#38; Skiena, S. (2024). The shape of word embeddings: Quantifying non-isometry with topological data analysis. In <i>Findings of the Association for Computational Linguistics: EMNLP 2024</i> (pp. 12080–12099). Miami, FL, United States: Association for Computational Linguistics. <a href=\"https://doi.org/10.18653/v1/2024.findings-emnlp.705\">https://doi.org/10.18653/v1/2024.findings-emnlp.705</a>"},"date_published":"2024-11-01T00:00:00Z","file":[{"date_created":"2025-02-10T08:20:34Z","relation":"main_file","file_id":"19016","access_level":"open_access","creator":"dernst","success":1,"file_size":1312638,"checksum":"f4416a5962194f0181ab0dc7f9ef93c0","content_type":"application/pdf","date_updated":"2025-02-10T08:20:34Z","file_name":"2024_EMNLP_Draganov.pdf"}],"publisher":"Association for Computational Linguistics","oa_version":"Published Version","conference":{"name":"EMNLP: Conference on Empirical Methods in Natural Language Processing","start_date":"2024-11-12","location":"Miami, FL, United States","end_date":"2024-11-16"},"title":"The shape of word embeddings: Quantifying non-isometry with topological data analysis","_id":"18998","type":"conference","has_accepted_license":"1","publication_status":"published","month":"11","doi":"10.18653/v1/2024.findings-emnlp.705","author":[{"first_name":"Ondrej","orcid":"0000-0003-0464-3823","id":"2B23F01E-F248-11E8-B48F-1D18A9856A87","full_name":"Draganov, Ondrej","last_name":"Draganov"},{"last_name":"Skiena","full_name":"Skiena, Steven","first_name":"Steven"}],"corr_author":"1","day":"01","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","image":"/images/cc_by.png"},"status":"public","year":"2024","language":[{"iso":"eng"}],"page":"12080-12099","ddc":["500"],"publication":"Findings of the Association for Computational Linguistics: EMNLP 2024","external_id":{"arxiv":["2404.00500"]},"article_processing_charge":"No","abstract":[{"lang":"eng","text":"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."}]}