Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Iustin Dornescu"'
Autor:
Iustin Dornescu, Constantin Orăsan
Publikováno v:
Natural Language Engineering. 20:469-500
This paper proposes a new method for semantic document analysis: densification, which identifies and ranks Wikipedia pages relevant to a given document. Although there are similarities with established tasks such as wikification and entity linking, t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::14aacee9f356013cc8fd587d4f2686fe
https://doi.org/10.1017/s1351324913000296
https://doi.org/10.1017/s1351324913000296
Publikováno v:
Proceedings of the Workshop on Automatic Text Simplification - Methods and Applications in the Multilingual Society (ATS-MA 2014).
This paper investigates non-destructive simplification, a type of syntactic text simplification which focuses on extracting embedded clauses from structurally complex sentences and rephrasing them without affecting their original meaning. This proces
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e5a3f39bab059349ce444306c9616d0
https://doi.org/10.3115/v1/w14-5601
https://doi.org/10.3115/v1/w14-5601
Publikováno v:
Proceedings of the Workshop on Automatic Text Simplification - Methods and Applications in the Multilingual Society (ATS-MA 2014).
In the state of the art, there are scarce resources available to support development and evaluation of automatic text simplification (TS) systems for specific target populations. These comprise parallel corpora consisting of texts in their original f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6967848e367b8bdf104abf5f71dc9428
https://doi.org/10.3115/v1/w14-5606
https://doi.org/10.3115/v1/w14-5606
Publikováno v:
PITR@EACL
Syntactically complex sentences constitute an obstacle for some people with Autistic Spectrum Disorders. This paper evaluates a set of simplification rules specifically designed for tackling complex and compound sentences. In total, 127 different rul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68cd6d91fa40521469f22873604af4fd
https://doi.org/10.3115/v1/w14-1215
https://doi.org/10.3115/v1/w14-1215
Publikováno v:
Text, Speech and Dialogue ISBN: 9783642327896
TSD
TSD
This paper describes a study of the impact of coreference resolution on NLP applications. Further to our previous study [1], in which we investigated whether anaphora resolution could be beneficial to NLP applications, we now seek to establish whethe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e3e50a911db5740670a46bc602588c13
https://doi.org/10.1007/978-3-642-32790-2_2
https://doi.org/10.1007/978-3-642-32790-2_2
Autor:
Christian Spurk, Rubén Izquierdo, Bernardo Magnini, Constantin Orasan, Matteo Negri, Óscar Ferrández, José Luis Vicedo, David Tomás, Iustin Dornescu, Sergio Ferrández, Guenter Neumann, Milen Kouylekov
Publikováno v:
SSRN Electronic Journal.
This paper presents the QALL-ME Framework, a reusable architecture for building multi- and cross-lingual Question Answering (QA) systems working on structured data modelled by an ontology. It is released as free open source software with a set of dem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::305c844c7ee0a039be32cec8da6e0a9a
https://doi.org/10.2139/ssrn.3199513
https://doi.org/10.2139/ssrn.3199513
Autor:
Iustin Dornescu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642157530
CLEF (1)
CLEF (1)
This paper presents a new question answering (QA) approach and a prototype system, EQUAL, which relies on structural information from Wikipedia to answer open-list questions. The system achieved the highest score amongst the participants in the GikiC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9abbd51317e132b1864e0b412ba791db
https://doi.org/10.1007/978-3-642-15754-7_39
https://doi.org/10.1007/978-3-642-15754-7_39
Autor:
Constatin Orasan, Iustin Dornescu
Publikováno v:
Proceedings of the 2009 Workshop on Language Generation and Summarisation - UCNLG+Sum '09.
This article presents the machine learning approach used by the University of Wolverhampton in the GREC-NEG'09 task. A classifier based on J48 decision tree and a meta-classifier were used to produce two runs. Evaluation on the development set shows
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3a71f17d893790fb0d90d090710bda2
https://doi.org/10.3115/1708155.1708177
https://doi.org/10.3115/1708155.1708177
Autor:
Alexandra Balahur, Dan Cristea, Diana Trandabăţ, Ionuţ Pistol, Diana Cotelea, Alex Moruz, Iuliana Drăghici, Iustin Dornescu, Adrian Iftene
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783540857594
CLEF
CLEF
This paper briefly describes UAIC's participation in this year's CLEF question answering competition, focusing on the main challenges and changes compared to our last year participation. An analysis of the errors introduced by each module is also dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8e1dfcbe623ac9739179fd86e17c287
https://doi.org/10.1007/978-3-540-85760-0_42
https://doi.org/10.1007/978-3-540-85760-0_42
Autor:
Dan Cristea, Ionuţ Pistol, Georgiana Puşcaşu, Adrian Iftene, Radu Ion, Alin Ceauşu, Diana Trandabăţ, Alex Moruz, Dan Tufis, Dan Stefanescu, Iustin Dornescu
Publikováno v:
Evaluation of Multilingual and Multi-modal Information Retrieval ISBN: 9783540749981
CLEF
CLEF
This paper describes the development of a Question Answering (QA) system and its evaluation results in the Romanian-English cross-lingual track organized as part of the CLEF 2006 campaign. The development stages of the cross-lingual Question Answerin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::346c78c464d6d03c239133c28be27a44
https://doi.org/10.1007/978-3-540-74999-8_46
https://doi.org/10.1007/978-3-540-74999-8_46