Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Ignacio Iacobacci"'
Autor:
Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11 (2023)
Externí odkaz:
https://doaj.org/article/4220f32916cb4863ba1b1964cc9857a1
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9 (2022)
Externí odkaz:
https://doaj.org/article/86ec9aa6f0ec4adca36e81bddb5941da
Publikováno v:
Findings of the Association for Computational Linguistics: ACL 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::501e4e79b84562dc52edec8c6708da7f
https://doi.org/10.18653/v1/2022.findings-acl.170
https://doi.org/10.18653/v1/2022.findings-acl.170
Autor:
Ignacio Iacobacci, Milan Gritta
Publikováno v:
ACL/IJCNLP (Findings)
The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource languages. Zero-s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2f9bb393f60451569e04c8df2dff7df
https://doi.org/10.18653/v1/2021.findings-acl.32
https://doi.org/10.18653/v1/2021.findings-acl.32
Publikováno v:
ACL/IJCNLP (Findings)
Transfer learning has become the dominant paradigm for many natural language processing tasks. In addition to models being pretrained on large datasets, they can be further trained on intermediate (supervised) tasks that are similar to the target tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::446fbf114dd9f448c4b68b50ba467912
Autor:
Ignacio Iacobacci, Ieva Staliunaite
Publikováno v:
ICASSP
Lately, joint training of Intent detection and Slot filling has become the best-performing approach in the field of Natural Language Understanding (NLU). In this work we extend the newly introduced application of Capsule Networks for NLU to a multi-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f524cf6e95e6447f771e03e802db94eb
https://doi.org/10.1109/icassp40776.2020.9053899
https://doi.org/10.1109/icassp40776.2020.9053899
Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size considering the complexity of the dialogues. Additionally, convent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::219923163a67a3c77af1e76d40d71122
Autor:
Ieva Staliūnaitė, Ignacio Iacobacci
Publikováno v:
EMNLP (1)
Many NLP tasks have benefited from transferring knowledge from contextualized word embeddings, however the picture of what type of knowledge is transferred is incomplete. This paper studies the types of linguistic phenomena accounted for by language
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a94384d0387a65e052c37a999bf8be1
https://doi.org/10.18653/v1/2020.emnlp-main.573
https://doi.org/10.18653/v1/2020.emnlp-main.573
Publikováno v:
ACL (1)
Recent years have seen a dramatic growth in the popularity of word embeddings mainly owing to their ability to capture semantic information from massive amounts of textual content. As a result, many tasks in Natural Language Processing have tried to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::328aed1761757de72377a1a90b622fb9
https://doi.org/10.18653/v1/p16-1085
https://doi.org/10.18653/v1/p16-1085
Publikováno v:
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
CoNLL
CoNLL
Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be automatically se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef09ebe93315189d2d2d800ca099eda9