A classification-based approach to cognate detection combining orthographic and semantic similarity information
- Author
- Sofie Labat (UGent) and Els Lefever (UGent)
- Organization
- Abstract
- This paper presents proof-of-concept experiments for combining orthographic and semantic information to distinguish cognates from non-cognates. To this end, a context-independent gold standard is developed by manually labelling English-Dutch pairs of cognates and false friends in bilingual term lists. These annotated cognate pairs are then used to train and evaluate a supervised binary classification system for the automatic detection of cognates. Two types of information sources are incorporated in the classifier: fifteen string similarity metrics capture form similarity between source and target words, while word embeddings model semantic similarity between the words. The experimental results show that even though the system already achieves good results by only incorporating orthographic information, the performance further improves by including semantic information in the form of embeddings.
- Keywords
- LT3
Downloads
-
publisher version.pdf
- full text (Published version)
- |
- open access
- |
- |
- 217.94 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8627333
- MLA
- Labat, Sofie, and Els Lefever. “A Classification-Based Approach to Cognate Detection Combining Orthographic and Semantic Similarity Information.” Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), edited by Galia Angelova et al., INCOMA Ltd., 2019, pp. 603–11, doi:10.26615/978-954-452-056-4_071.
- APA
- Labat, S., & Lefever, E. (2019). A classification-based approach to cognate detection combining orthographic and semantic similarity information. In G. Angelova, R. Mitkov, I. Nikolova, & I. Temnikova (Eds.), Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019) (pp. 603–611). https://doi.org/10.26615/978-954-452-056-4_071
- Chicago author-date
- Labat, Sofie, and Els Lefever. 2019. “A Classification-Based Approach to Cognate Detection Combining Orthographic and Semantic Similarity Information.” In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), edited by Galia Angelova, Ruslan Mitkov, Ivelina Nikolova, and Irina Temnikova, 603–11. INCOMA Ltd. https://doi.org/10.26615/978-954-452-056-4_071.
- Chicago author-date (all authors)
- Labat, Sofie, and Els Lefever. 2019. “A Classification-Based Approach to Cognate Detection Combining Orthographic and Semantic Similarity Information.” In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), ed by. Galia Angelova, Ruslan Mitkov, Ivelina Nikolova, and Irina Temnikova, 603–611. INCOMA Ltd. doi:10.26615/978-954-452-056-4_071.
- Vancouver
- 1.Labat S, Lefever E. A classification-based approach to cognate detection combining orthographic and semantic similarity information. In: Angelova G, Mitkov R, Nikolova I, Temnikova I, editors. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019). INCOMA Ltd.; 2019. p. 603–11.
- IEEE
- [1]S. Labat and E. Lefever, “A classification-based approach to cognate detection combining orthographic and semantic similarity information,” in Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), Varna, Bulgaria, 2019, pp. 603–611.
@inproceedings{8627333,
abstract = {{This paper presents proof-of-concept experiments for combining orthographic and semantic information to distinguish cognates from non-cognates. To this end, a context-independent gold standard is developed by manually labelling English-Dutch pairs of cognates and false friends in bilingual term lists. These annotated cognate pairs are then used to train and evaluate a supervised binary classification system for the automatic detection of cognates. Two types of information sources are incorporated in the classifier: fifteen string similarity metrics capture form similarity between source and target words, while word embeddings model semantic similarity between the words. The experimental results show that even though the system already achieves good results by only incorporating orthographic information, the performance further improves by including semantic information in the form of embeddings.}},
author = {{Labat, Sofie and Lefever, Els}},
booktitle = {{Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)}},
editor = {{Angelova, Galia and Mitkov, Ruslan and Nikolova, Ivelina and Temnikova, Irina}},
isbn = {{9789544520557}},
issn = {{1313-8502}},
keywords = {{LT3}},
language = {{eng}},
location = {{Varna, Bulgaria}},
pages = {{603--611}},
publisher = {{INCOMA Ltd.}},
title = {{A classification-based approach to cognate detection combining orthographic and semantic similarity information}},
url = {{http://doi.org/10.26615/978-954-452-056-4_071}},
year = {{2019}},
}
- Altmetric
- View in Altmetric