Building a supertagger for Spanish HPSG

Autor: Dina Wonsever, Luis Chiruzzo

Publikováno v: Computer Speech & Language. 54:44-60

We created a supertagger for the Spanish language aimed at disambiguating the HPSG lexical frames for the verbs, nouns and adjectives in a sentence. The supertagger uses a maximum entropy model and achieves an accuracy of 84.16% over the verb classes

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1d9205b574b40172f9d087d5478eac68
https://doi.org/10.1016/j.csl.2018.08.005

Statistical Deep Parsing for Spanish Using Neural Networks

Autor: Dina Wonsever, Luis Chiruzzo

Publikováno v: IWPT 2020

This paper presents the development of a deep parser for Spanish that uses a HPSG grammar and returns trees that contain both syntactic and semantic information. The parsing process uses a top-down approach implemented using LSTM neural networks, and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4ef164c3c3640a24ee80caf1da4a8a47
https://doi.org/10.18653/v1/2020.iwpt-1.14

TEMANTEX: A Markup Language for Spanish Temporal Expressions and Indicators

Autor: Aiala Rosá, Mathias Etcheverry, Marisa Malcuori, Dina Wonsever

Publikováno v: Research in Computing Science. 97:9-19

We describe the TEMANTEX annotation scheme for temporal expressions and other lexical indicators of temporality and we analyze a first annotation experience. TEMANTEX is mainly a revision of the markup language TIMEX3, but with some additions and a d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ebfe9068103bdbbdde8c466cc2ce2262
https://doi.org/10.13053/rcs-97-1-1

Supertagging for a Statistical HPSG Parser for Spanish

Autor: Luis Chiruzzo, Dina Wonsever

Publikováno v: Statistical Language and Speech Processing ISBN: 9783319257884
SLSP

We created a supertagger for the Spanish language aimed at disambiguating the HPSG lexical frames for the verbs in a sentence. The supertagger uses a CRF model and achieves an accuracy of 83.58i¾ź% for the verb classes on the test set. The tagset c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9b3388d4d6829ac9d46e7e203f935b49
https://doi.org/10.1007/978-3-319-25789-1_3

The Influence of Syntactic Information on Hedge Scope Detection

Autor: Dina Wonsever, Guillermo Moncecchi, Jean-Luc Minel

Publikováno v: Lecture Notes in Computer Science
Advances in Artificial Intelligence--IBERAMIA 2014
Ana L.C. Bazzan, Karim Pichara. Advances in Artificial Intelligence--IBERAMIA 2014, springer-Verlag, pp.83-94, 2014, 14th Ibero-American Conference on AI, 978-3-319-12026-3. ⟨10.1007/978-3-319-12027-0_7⟩
Ana L.C. Bazzan, Karim Pichara. Advances in Artificial Intelligence--IBERAMIA 2014, 8864, springer-Verlag, pp.83-94, 2014, 14th Ibero-American Conference on AI, 978-3-319-12026-3. ⟨10.1007/978-3-319-12027-0_7⟩
Advances in Artificial Intelligence--IBERAMIA 2014 ISBN: 9783319120263
IBERAMIA

International audience; In this paper we elaborate over the use of sequential super-vised learning methods on the task of hedge cue scope detection. We address the task using a learning methodology that proposes the use of an iterative, error-based a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1dc951764b394d99fe56bfbc98dada2b
https://halshs.archives-ouvertes.fr/halshs-01086214/document