Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Pierluigi Cassotti"'
Publikováno v:
IJCoL, Vol 6, Iss 2, Pp 23-36 (2020)
In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stab
Externí odkaz:
https://doaj.org/article/cee9d6258dfc4bf4b3dcfac6e9d23ebe
Publikováno v:
IJCoL, Vol 3, Iss 2, Pp 37-50 (2017)
In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM,
Externí odkaz:
https://doaj.org/article/a0c725c2e96d416e80f81c6a548eeff1
Publikováno v:
IJCoL, Vol 6, Iss 2, Pp 23-36 (2020)
In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c460e402bd9ca906a7b8e66053b5092
http://journals.openedition.org/ijcol/714
http://journals.openedition.org/ijcol/714
Publikováno v:
Scopus-Elsevier
The grammatical gender system can influence the way the semantic gender is perceived. Italian is a grammatical gender language, in which nouns are classified for gender. In this work, we investigate the usage of gender-specific forms of occupational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b93803b7d79880e69497c8f1e0edd1ea
https://doi.org/10.4000/books.aaccademia.10907
https://doi.org/10.4000/books.aaccademia.10907
Publikováno v:
Scopus-Elsevier
This paper describes the first edition of the “Diachronic Lexical Seman-tics” (DIACR-Ita) task at the EVALITA2020 campaign. The task challenges participants to develop systems that can automatically detect if a given word has changed its meaning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31f1bdfe181af7f9d3add32ac959b943
https://doi.org/10.4000/books.aaccademia.7613
https://doi.org/10.4000/books.aaccademia.7613
Publikováno v:
CLiC-it 2020 Italian Conference on Computational Linguistics 2020: Proceedings of the Seventh Italian Conference on Computational Linguistics, 2769
University of Groningen
Scopus-Elsevier
Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 ISBN: 9791280136336
University of Groningen
Scopus-Elsevier
Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 ISBN: 9791280136336
In this paper, we describe the creation of a diachronic corpus for Italian by exploiting the digital archive of the newspaper “L’Unit`a”. We automatically clean and annotate the corpus with PoStags, lemmas, named entities and syntactic dependen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d6b22328980f86327cb8c992da556d7
https://research.rug.nl/en/publications/260bd585-a879-48d1-89c8-6b4e9f402671
https://research.rug.nl/en/publications/260bd585-a879-48d1-89c8-6b4e9f402671
Publikováno v:
SemEval@COLING
Cassotti, Pierluigi, Caputo, Annalina ORCID: 0000-0002-7144-8545, Polignano, Marco ORCID: 0000-0002-3939-0136 and Basile, Pierpaolo ORCID: 0000-0002-0545-1105 (2020) GM-CTSC at SemEval-2020 Task 1: Gaussian mixtures cross temporal similarity clustering. In: Fourteenth Workshop on Semantic Evaluation, Dec 2020, Barcelona (Online).
Cassotti, Pierluigi, Caputo, Annalina ORCID: 0000-0002-7144-8545
This paper describes the system proposed by the Random team for SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. We focus our approach on the detection problem. Given the semantics of words captured by temporal word embeddings in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c2eb77265ebf7f1e5e83af2cf927c48
https://doi.org/10.18653/v1/2020.semeval-1.7
https://doi.org/10.18653/v1/2020.semeval-1.7
Publikováno v:
IJCoL, Vol 3, Iss 2, Pp 37-50 (2017)
In this paper, we propose a Deep Learning architecture for several Italian Natural Language Processing tasks based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b420b97ef5869c5f8598a64e914b48a1
https://doi.org/10.4000/ijcol.553
https://doi.org/10.4000/ijcol.553
Publikováno v:
Scopus-Elsevier
CLiC-it
CLiC-it
With the growing availability of digitized diachronic corpora, the need for tools capable of taking into account the diachronic component of corpora becomes ever more pressing. Recent works on diachronic embeddings show that computational approaches
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d8d352844680999b43e6e23b7dc2ba6
http://www.scopus.com/inward/record.url?eid=2-s2.0-85097878805&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85097878805&partnerID=MN8TOARS
Publikováno v:
Scopus-Elsevier
CLiC-it
CLiC-it
In this paper, we propose a Deep Learning architecture for sequence labeling based on a state of the art model that exploits both word- and character-level representations through the combination of bidirectional LSTM, CNN and CRF. We evaluate the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75cb48720eb97b27e9968d228496cb71
http://www.scopus.com/inward/record.url?eid=2-s2.0-85037355606&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85037355606&partnerID=MN8TOARS