Proisl T, Lapesa G (2020)
Publication Language: English
Publication Type: Conference contribution, Original article
Publication year: 2020
Publisher: CEUR-WS.org
Conference Proceedings Title: Proceedings of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2020)
Event location: Online
URI: http://ceur-ws.org/Vol-2765/paper140.pdf
DOI: 10.4000/books.aaccademia.7780
Open Access Link: http://ceur-ws.org/Vol-2765/paper140.pdf
In this paper, we describe experiments on part-of-speech tagging of spoken Italian that we conducted in the context of the EVALITA 2020 KIPoS shared task (Bosco et al., 2020). Our submission to the shared task is based on SoMeWeTa (Proisl, 2018), a tagger which supports domain adaptation and is designed to flexibly incorporate external resources. We document our approach and discuss our results in the shared task along with a statistical analysis of the factors which impact performance the most. Additionally, we report on a set of additional experiments involving the combination of neural language models with unsupervised HMMs, and compare its performance to that of our system.
APA:
Proisl, T., & Lapesa, G. (2020). KLUMSy@KIPoS: Experiments on Part-of-Speech Tagging of Spoken Italian. In Basile V, Croce D, Di Maro M, Passaro L (Eds.), Proceedings of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2020). Online: CEUR-WS.org.
MLA:
Proisl, Thomas, and Gabriella Lapesa. "KLUMSy@KIPoS: Experiments on Part-of-Speech Tagging of Spoken Italian." Proceedings of the 7th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian (EVALITA 2020), Online Ed. Basile V, Croce D, Di Maro M, Passaro L, CEUR-WS.org, 2020.
BibTeX: Download