Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Marinela Parovic"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 410-428 (2021)
AbstractMost combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task–language combinations with
Externí odkaz:
https://doaj.org/article/92cb939b996e45739395143686969d16
Autor:
Sarfraz Khurshid, Aleksandar Milicevic, Zhiqiang Zang, Milos Gligoric, Marinela Parovic, Pengyu Nie
Publikováno v:
Proceedings of the ACM on Programming Languages. 4:1-26
We present Deuterium---a framework for implementing Java methods as executable contracts. Deuterium introduces a novel, type-safe way to write method contracts entirely in Java, as a combination of imperative generators and declarative specifications
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8869d3099ce4278fa8dbdb9c67b34c13
https://doi.org/10.1145/3428285
https://doi.org/10.1145/3428285
Autor:
Ryan Cotterell, Edoardo Maria Ponti, Ivan Vulić, Roi Reichart, Anna Korhonen, Marinela Parovic
Publikováno v:
Transactions of the Association for Computational Linguistics, 9
Transactions of the Association for Computational Linguistics
Ponti, E M, Vulić, I, Cotterell, R, Parovic, M, Reichart, R & Korhonen, A 2021, ' Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages ', Transactions of the Association for Computational Linguistics, vol. 9, pp. 410-428 . https://doi.org/10.1162/tacl_a_00374
Transactions of the Association for Computational Linguistics
Ponti, E M, Vulić, I, Cotterell, R, Parovic, M, Reichart, R & Korhonen, A 2021, ' Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages ', Transactions of the Association for Computational Linguistics, vol. 9, pp. 410-428 . https://doi.org/10.1162/tacl_a_00374
Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task–language combinations with availab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5eb986088f749171b9ef555f469a7700
http://arxiv.org/abs/2001.11453
http://arxiv.org/abs/2001.11453
Publikováno v:
34th International Conference on Automated Software Engineering (ASE 2019
34th International Conference on Automated Software Engineering (ASE 2019, Nov 2019, San Diego, United States
ASE
34th International Conference on Automated Software Engineering (ASE 2019, Nov 2019, San Diego, United States
ASE
International audience; Mutation analysis, which introduces artificial defects into software systems, is the basis of mutation testing, a technique widely applied to evaluate and enhance the quality of test suites. However, despite the deep analogy b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a87d60e298025a501d499572d457b2c5
https://hal-mines-paristech.archives-ouvertes.fr/hal-02434236/document
https://hal-mines-paristech.archives-ouvertes.fr/hal-02434236/document