Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Debora Nozza"'
Publikováno v:
Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c9335f46586cdd14d81c4907369df2c
https://doi.org/10.18653/v1/2022.ltedi-1.4
https://doi.org/10.18653/v1/2022.ltedi-1.4
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a19ef4d5f710ce64ad5eb6714ddb04ae
Publikováno v:
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4234c71f3a472ccaebee8e82dadf9222
https://doi.org/10.18653/v1/2022.nlppower-1.11
https://doi.org/10.18653/v1/2022.nlppower-1.11
Publikováno v:
Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d140d9eea680f6c82803528ae0efde2b
https://doi.org/10.18653/v1/2022.bigscience-1.6
https://doi.org/10.18653/v1/2022.bigscience-1.6
Publikováno v:
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::45d72bf8914c0d6064897b6617a79f39
https://doi.org/10.18653/v1/2022.woah-1.24
https://doi.org/10.18653/v1/2022.woah-1.24
Publikováno v:
Building Simulation Conference Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1302ddd04b811581dc212e35e3c18d74
https://doi.org/10.26868/25222708.2021.30193
https://doi.org/10.26868/25222708.2021.30193
The task of Named Entity Recognition (NER) is aimed at identifying named entities in a given text and classifying them into pre-defined domain entity types such as persons, organizations, locations. Most of the existing NER systems make use of generi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dba3a372d4b92c4b35da449677a17f46
http://hdl.handle.net/10281/305636
http://hdl.handle.net/10281/305636
Publikováno v:
EACL
Scopus-Elsevier
Scopus-Elsevier
Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d3dc55472174a3465c32d513304db6a
http://hdl.handle.net/11565/4042491
http://hdl.handle.net/11565/4042491