Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Lonneke, van der Plas"'
Autor:
Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
Publikováno v:
Computational Linguistics, Vol 43, Iss 4 (2017)
Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction betw
Externí odkaz:
https://doaj.org/article/1915b7472b9146c6b3d25f9ce3303ccc
Autor:
Lonneke van der Plas, Patrick Ziering
Publikováno v:
Word Structure. 13:250-281
In this paper, we present an empirical study on the definition of compounds in English, the graded nature of the phenomenon and its correlations with the commonly used linguistic criteria for compoundhood. We create a resource that includes a diverse
Autor:
Lonneke van der Plas, Albert Gatt, Aitor García Pablos, Elena Edelman, Ángela Franco Torres, Khalid Choukri, Hans Degroote, Roberts Rozis, Thomas Lavergne, Pierre Zweigenbaum, Manuel Herranz, Thierry Etchegoyhen, Victoria Arranz, Mike Rosner, Claudia Borg, Montse Cuadros, Aleix Cerdà, Maite Melero, Ona de Gibert, Rinalds Vīksna, Cyril Grouin, Lucie Gianola, Chomicha Bendahman, Patrick Paroubek, Laurent Bié, Alejandro Adolfo Kohan, Ēriks Ajausks, Mickaël Rigault, Mercedes García Hernandez
Publikováno v:
Legal Knowledge and Information Systems
Frontiers in Artificial Intelligence and Applications
International Conference on Legal Knowledge and Information Systems
International Conference on Legal Knowledge and Information Systems, Dec 2020, Brno, Prague, Czech Republic. pp.223-226, ⟨10.3233/FAIA200869⟩
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
JURIX
Frontiers in Artificial Intelligence and Applications
International Conference on Legal Knowledge and Information Systems
International Conference on Legal Knowledge and Information Systems, Dec 2020, Brno, Prague, Czech Republic. pp.223-226, ⟨10.3233/FAIA200869⟩
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
JURIX
The European MAPA (Multilingual Anonymisation for Public Administrations) project aims at developing an open-source solution for automatic de-identification of medical and legal documents. We introduce here the context, partners and aims of the proje
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f93457660a7043681d043fb9e916c36
https://hal.archives-ouvertes.fr/hal-03058311
https://hal.archives-ouvertes.fr/hal-03058311
Publikováno v:
1st International Workshop on Computational Approaches to Historical Language Change: Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, 234-239
STARTPAGE=234;ENDPAGE=239;TITLE=1st International Workshop on Computational Approaches to Historical Language Change
STARTPAGE=234;ENDPAGE=239;TITLE=1st International Workshop on Computational Approaches to Historical Language Change
We present work in progress on the temporal progression of compositionality in noun-noun compounds. Previous work has proposed computational methods for determining the compositionality of compounds. These methods try to automatically determine how t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a82144a4d6e5498861625b4bf2d3ad78
https://research.rug.nl/en/publications/8ffdffed-6e7d-4e46-9c06-2fe4089aa498
https://research.rug.nl/en/publications/8ffdffed-6e7d-4e46-9c06-2fe4089aa498
Autor:
Prajit Dhar, Lonneke van der Plas
Publikováno v:
Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019): Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), 30-39
STARTPAGE=30;ENDPAGE=39;TITLE=Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
MWE-WN@ACL
STARTPAGE=30;ENDPAGE=39;TITLE=Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
MWE-WN@ACL
We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus. We train compositional models on observed compounds, more specifically
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::09477989a026e89f2ae599332f492c89
https://hdl.handle.net/11370/928a7795-aad3-4ae8-98de-4b6f41230377
https://hdl.handle.net/11370/928a7795-aad3-4ae8-98de-4b6f41230377
Autor:
Savary, Agata, Marie Candito, Verginica Barbu Mititelu, Eduard Bejček, Fabienne Cap, Slavomír Čéplö, Silvio Ricardo Cordeiro, Gülşen Eryiğit, Voula Giouli, Maarten van Gompel, Yaakov HaCohen-Kerner, Jolanta Kovalevskaitė, Simon Krek, Chaya Liebeskind, Johanna Monti, Carla Parra Escartín, Lonneke van der Plas, Behrang QasemiZadeh, Carlos Ramisch, Federico Sangati, Ivelina Stoyanova, Veronika Vincze
Publikováno v:
Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop, 2018
BASE-Bielefeld Academic Search Engine
Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop, 2018
BASE-Bielefeld Academic Search Engine
Multiword expressions (MWEs) are known as a “pain in the neck” due to their idiosyncratic behaviour. While some categories of MWEs have been largely stud- ied, verbal MWEs (VMWEs) such as to take a walk, to break one’s heart or to turn off have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::154cb5e2ac0b890b2665015d5ff0a568
https://hal.archives-ouvertes.fr/hal-01917174/document
https://hal.archives-ouvertes.fr/hal-01917174/document
Autor:
Monti, Johanna, Agata, Savary, Marie, Candito, Verginica Barbu Mititelu, Eduard, Bejček, Fabienne, Cap, Slavomir, Čéplö, Silvio Ricardo Cordeiro, Gülşen, Eryiğit, Voula, Giouli, Maarten van Gompel, Yaakov, HaCohen-Kerner, Jolanta, Kovalevskaitė, Simon, Krek, Chaya, Liebeskind, Carla Parra Escartín, Lonneke van der Plas, Behrang, Qasemizadeh, Carlos, Ramisch, Sangati, Federico, Ivelina, Stoyanova, Veronika, Vincze
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3684::1570aa86a90bc3876b5025f58a0e766a
http://hdl.handle.net/11574/183478
http://hdl.handle.net/11574/183478
Autor:
Gülşen Eryiğit, Lonneke van der Plas, Johanna Monti, Amalia Todirascu, Mathieu Constant, Mike Rosner, Carlos Ramisch
Publikováno v:
Computational Linguistics
Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2017, 43 (4), pp.837-892. ⟨10.1162/COLI_a_00302⟩
Computational Linguistics, 2017, 43 (4), pp.837-892. ⟨10.1162/COLI_a_00302⟩
Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2017, 43 (4), pp.837-892. 〈http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00302〉. 〈10.1162/COLI_a_00302〉
Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2017, 43 (4), pp.837-892. ⟨10.1162/COLI_a_00302⟩
Computational Linguistics, 2017, 43 (4), pp.837-892. ⟨10.1162/COLI_a_00302⟩
Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2017, 43 (4), pp.837-892. 〈http://www.mitpressjournals.org/doi/abs/10.1162/COLI_a_00302〉. 〈10.1162/COLI_a_00302〉
International audience; Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::07e7bb4bfa8736e13d6286e9d5464ff8
https://halshs.archives-ouvertes.fr/halshs-01665254
https://halshs.archives-ouvertes.fr/halshs-01665254
Publikováno v:
ACL (2)
Traditionally, compound splitters are evaluated intrinsically on gold-standard data or extrinsically on the task of statistical machine translation. We explore a novel way for the extrinsic evaluation of compound splitters, namely recognizing textual
Publikováno v:
RepEval@EMNLP
System using BiLSTM and max pooling. Embedding is enhanced by POS, character and dependency info.