Abstract
We present our contribution to the EvaLatin shared task, which is the first evaluation campaign devoted to the evaluation of NLP tools for Latin. We submitted a system based on UDPipe 2.0, one of the winners of the CoNLL 2018 Shared Task, The 2018 Shared Task on Extrinsic Parser Evaluation and SIGMORPHON 2019 Shared Task. Our system places first by a wide margin both in lemmatization and POS tagging in the open modality, where additional supervised data is allowed, in which case we utilize all Universal Dependency Latin treebanks. In the closed modality, where only the EvaLatin training data is allowed, our system achieves the best performance in lemmatization and in classical subtask of POS tagging, while reaching second place in cross-genre and cross-time settings. In the ablation experiments, we also evaluate the influence of BERT and XLM-RoBERTa contextualized embeddings, and the treebank encodings of the different flavors of Latin treebanks.- Anthology ID:
- 2020.lt4hala-1.20
- Volume:
- Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Editors:
- Rachele Sprugnoli, Marco Passarotti
- Venue:
- LT4HALA
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 124–129
- Language:
- English
- URL:
- https://aclanthology.org/2020.lt4hala-1.20
- DOI:
- Cite (ACL):
- Milan Straka and Jana Straková. 2020. UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 124–129, Marseille, France. European Language Resources Association (ELRA).
- Cite (Informal):
- UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings (Straka & Straková, LT4HALA 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.lt4hala-1.20.pdf