Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{48309,
author = {Schmalz, Verena and Frey, JenniferandCarmen and Stemle, Egon},
address = {Milan, Italy},
booktitle = {8th Italian Conference on Computational Linguistics, CLiC-it 2021},
keywords = {PoS tagging; automatic evaluation},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Milan, Italy},
pages = {1-7},
publisher = {CEUR Workshop Proceedings},
title = {Introducing a Gold Standard Corpus from Young Multilinguals for the Evaluation of Automatic UD-PoS Taggers for Italian},
url = {http://ceur-ws.org/Vol-3033/paper13.pdf},
year = {2021}
}
TY - JOUR
ID - 48309
AU - Schmalz, Verena - Frey, Jennifer-Carmen - Stemle, Egon
PY - 2021
TI - Introducing a Gold Standard Corpus from Young Multilinguals for the Evaluation of Automatic UD-PoS Taggers for Italian
PB - CEUR Workshop Proceedings
CY - Milan, Italy
KW - PoS tagging
KW - automatic evaluation
UR - http://ceur-ws.org/Vol-3033/paper13.pdf
N2 - Part-of-speech (PoS) tagging constitutes a common task in Natural Language Processing (NLP), given its widespread applicability. However, with the advance of new information technologies and language variation, the contents and methods for PoS-tagging have changed. The majority of Italian existing data for this task originate from standard texts, where language use is far from multifaceted informal real-life situations. Automatic PoS-tagging models trained with such data do not perform reliably on non-standard language, like social media content or language learners’ texts. Our aim is to provide additional training and evaluation data from language learners tagged in Universal Dependencies (UD), as well as testing current automatic PoStagging systems and evaluating their performance on such data. We use a multilingual corpus of young language learners, LEONIDE, to create a tagged gold standard for evaluating UD PoStagging performance on the Italian nonstandard language. With the 3.7 version of Stanza, a Python NLP package, we apply available automatic PoS-taggers, namely ISDT, ParTUT, POSTWITA, TWITTIRÒ and VIT, trained with both standard and non-standard data, on our dataset. Our results show that the above taggers, trained on non-standard data or multilingual Treebanks, can achieve up to 95% of accuracy on multilingual learner data, if combined.
ER -
SCHMALZ, Verena, Jennifer-Carmen FREY a Egon STEMLE. Introducing a Gold Standard Corpus from Young Multilinguals for the Evaluation of Automatic UD-PoS Taggers for Italian. Online. In \textit{8th Italian Conference on Computational Linguistics, CLiC-it 2021}. Milan, Italy: CEUR Workshop Proceedings, 2021, s.~1-7. ISSN~1613-0073.
|
