Filtri
cris logo
-
Novo iskanje Filtri
Izberi iz seznama
Prikazano od Prikaži več
Dosegli ste najvišje možno število prikazanih rezultatov iskanja.
Prikazani so vsi rezultati
Za izvedeno iskanje ni na voljo rezultatov
Prikazano od
Dosegli ste najvišje možno število prikazanih rezultatov iskanja.
Prikazani so vsi rezultati
Nalaganje rezultatov
Pridobivanje statističnih podatkov

Mednarodni projekti vir: SICRIS

Parsing and multi-word expressions. Towards linguistic precision and computational efficiency in natural language processing (PARSEME)

Uredi
Raziskovalci (1)
št. Evidenčna št. Ime in priimek Razisk. področje Vloga Obdobje Štev. publikacij
1.  26294  dr. Darja Fišer  Jezikoslovje  Vodja  2013 - 2017  412 
Organizacije (1)
št. Evidenčna št. Razisk. organizacija Kraj Matična številka Štev. publikacij
1.  0581  Univerza v Ljubljani, Filozofska fakulteta  Ljubljana  1627058  97.976 
Povzetek
This Action aims at increasing and enhancing the support of the European multilingual heritage from Information and Communication Technologies (ICT). This general aim is addressed through improving linguistic representativeness, precision and computational efficiency of Natural Language Processing (NLP) applications. The Action focuses on the major bottleneck of these applications: Multi-Word Expressions (MWEs), i.e. sequences of words with unpredictable properties such as to count somebody in or to take a haircut. A breakthrough in their modelling and processing can only result from a coordinated effort of multidisciplinary experts in different languages. COST is the most adequate framework answering this need. Fourteen European languages will be addressed from a cross-theoretical and cross-methodological perspective, necessary for coping with current fragmentation issues. Expected deliverables include enhanced language resources and tools, as well as recommendations of best practices for cutting-edge MWE-aware language models. The Action will lead to a better understanding of the nature of MWEs. It will establish a long-lasting collaboration within a multilingual network of MWE specialists. It will pave the way towards competitive next generation text processing tools which will pay greater attention to language phenomena.
Zahtevana je potrditev
Zgodovina ogledov
Priljubljeno