Abstract
This study evaluates three different lemmatization approaches to Estonian—Generative character-level models, Pattern-based word-level classification models, and rule-based morphological analysis. According to our experiments, a significantly smaller Generative model consistently outperforms the Pattern-based classification model based on EstBERT. Additionally, we observe a relatively small overlap in errors made by all three models, indicating that an ensemble of different approach could lead to improvements.- Anthology ID:
- 2023.nodalida-1.28
- Volume:
- Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
- Month:
- May
- Year:
- 2023
- Address:
- Tórshavn, Faroe Islands
- Editors:
- Tanel Alumäe, Mark Fishel
- Venue:
- NoDaLiDa
- SIG:
- Publisher:
- University of Tartu Library
- Note:
- Pages:
- 280–285
- Language:
- URL:
- https://aclanthology.org/2023.nodalida-1.28
- DOI:
- Cite (ACL):
- Aleksei Dorkin and Kairit Sirts. 2023. Comparison of Current Approaches to Lemmatization: A Case Study in Estonian. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 280–285, Tórshavn, Faroe Islands. University of Tartu Library.
- Cite (Informal):
- Comparison of Current Approaches to Lemmatization: A Case Study in Estonian (Dorkin & Sirts, NoDaLiDa 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2023.nodalida-1.28.pdf