JHUBC’s Submission to LT4HALA EvaLatin 2020

Winston Wu, Garrett Nicolai


Abstract
We describe the JHUBC submission to the EvaLatin Shared task on lemmatization and part-of-speech tagging for Latin. We modify a hard-attentional character-based encoder-decoder to produce lemmas and POS tags with separate decoders, and to incorporate contextual tagging cues. While our results show that the dual decoder approach fails to encode data as successfully as the single encoder, our simple context incorporation method does lead to modest improvements.
Anthology ID:
2020.lt4hala-1.18
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:
114–118
Language:
English
URL:
https://aclanthology.org/2020.lt4hala-1.18
DOI:
Bibkey:
Cite (ACL):
Winston Wu and Garrett Nicolai. 2020. JHUBC’s Submission to LT4HALA EvaLatin 2020. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 114–118, Marseille, France. European Language Resources Association (ELRA).
Cite (Informal):
JHUBC’s Submission to LT4HALA EvaLatin 2020 (Wu & Nicolai, LT4HALA 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lt4hala-1.18.pdf