Výsledky vyhledávání

Akademický článek

Extracting information from participial structures

Autor: Enikö Héja, Kata Gábor

Publikováno v: Anuario del Seminario de Filología Vasca "Julio de Urquijo", Vol 41, Iss 2 (2007)

Our applied linguistic research aims at increasing the efficiency of a rule-based information extraction (IE) system by enhancing it with further grammatical knowledge. The input of the IE system is made up of sentences of business news. The event of

Externí odkaz: https://doaj.org/article/1fc51029cbb34e18bb61fee4abaa841d

Zobrazit plný text záznamu

Akademický článek

Complements and adjuncts in machine translation

Autor: Kata Gábor, Enikö Héja

Publikováno v: Anuario del Seminario de Filología Vasca "Julio de Urquijo", Vol 41, Iss 2 (2007)

A significant number of natural language processing applications cannot work without syntactic parsing. The automatic syntactic analysis of natural language texts in turn requires an efficient method for differentiating between elements that belong t

Externí odkaz: https://doaj.org/article/4068bdb7968346ce8e9aa66364262769

Zobrazit plný text záznamu

Emergence of Syntax Needs Minimal Supervision

Autor: Raphaël Bailly, Kata Gábor

Publikováno v: ACL 2020
ACL 2020, Jul 2020, Seattle, United States
ACL

This paper is a theoretical contribution to the debate on the learnability of syntax from a corpus without explicit syntax-specific guidance. Our approach originates in the observable structure of a corpus, which we use to define and isolate grammati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3e674fdaf27087b37f9451d36b32dd6

Zobrazit plný text záznamu

Integrating Dependency Parses with Sequential Patterns to Improve Relation Extraction

Autor: Kata Gábor, Nadège Lechevrel, Isabelle Tellier, Thierry Charnois, Haifa Zargayouna, Davide Buscaldi

Publikováno v: TALN 2018
TALN 2018, May 2018, Rennes, France
HAL

In this paper, we investigate the contribution of syntactic features to the task of unsupervised clustering of semantic relation instances. Instances, i.e. couples of concepts appearing in scientific texts, are represented in a couple-pattern matrix

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d9d9f2f69b6668805506459e5ceb8c0e
https://hal.inria.fr/hal-02079719

Zobrazit plný text záznamu

SemEval-2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers

Autor: Thierry Charnois, Behrang QasemiZadeh, Kata Gábor, Haïfa Zargayouna, Davide Buscaldi, Anne-Kathrin Schumann

Publikováno v: SemEval@NAACL-HLT
International Workshop on Semantic Evaluation (SemEval-2018)
International Workshop on Semantic Evaluation (SemEval-2018), Jun 2017, New Orleans, United States. pp.679-688

International audience; This paper describes the first task on semantic relation extraction and classification in scientific paper abstracts at SemEval 2018. The challenge focuses on domain-specific semantic relations and includes three different sub

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d609d16550e47f214ea1c241ffcfc3c
https://doi.org/10.18653/v1/s18-1111

Zobrazit plný text záznamu

Exploring Vector Spaces for Semantic Relations

Autor: Isabelle Tellier, Kata Gábor, Thierry Charnois, Davide Buscaldi, Haïfa Zargayouna

Publikováno v: EMNLP

Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words. Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities. In th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::86e86f730bcd7697789bc1cd6e2ed1ed
https://doi.org/10.18653/v1/d17-1193

Zobrazit plný text záznamu

Unsupervised Relation Extraction in Specialized Corpora Using Sequence Mining

Autor: Kata Gábor, Haïfa Zargayouna, Thierry Charnois, Isabelle Tellier, Davide Buscaldi

Publikováno v: Lecture Notes in Computer Science ISBN: 9783319463483
IDA
XVIth Symposium on Intelligent Data Analysis
XVIth Symposium on Intelligent Data Analysis, Oct 2016, Stockholm, Sweden. pp.237-248, ⟨10.1007/978-3-319-46349-0_21⟩

International audience; This paper deals with the extraction of semantic relations from scientific texts. Pattern-based representations are compared to word embeddings in unsupervised clustering experiments, according to their potential to discover n

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fdefb33073751a8c49ae7d328e1addfb
https://doi.org/10.1007/978-3-319-46349-0_21

Zobrazit plný text záznamu

Automated Error Detection in Digitized Cultural Heritage Documents

Autor: Kata Gábor, Benoît Sagot

Publikováno v: EACL 2014 Workshop on Language Technology for Cultural Heritage
EACL 2014 Workshop on Language Technology for Cultural Heritage, Apr 2014, Göteborg, Sweden
LaTeCH@EACL
EACL 2014 Workshop on Language Technology for Cultural Heritage, Apr 2014, Göteborg, Sweden. 2014

International audience; The work reported in this paper aims at performance optimization in the digitization of documents pertaining to the cultural heritage domain. A hybrid method is roposed, combining statistical classification algorithms and ling

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7bcc55cad6ecdf76e838b690de705512
https://hal.inria.fr/hal-01022402/file/W14-0608.pdf

Zobrazit plný text záznamu

Clustering Hungarian verbs on the basis of complementation patterns

Autor: Kata Gábor, Enikő Héja

Publikováno v: ACL

Our paper reports an attempt to apply an unsupervised clustering algorithm to a Hungarian treebank in order to obtain semantic verb classes. Starting from the hypothesis that semantic metapredicates underlie verbs' syntactic realization, we investiga

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7541aae871a7275035f4735eb8036f40
https://doi.org/10.3115/1557835.1557855

Zobrazit plný text záznamu

Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature

Autor: Kata Gábor, Haïfa Zargayouna, Davide Buscaldi, Isabelle Tellier, Thierry Charnois

Publikováno v: HAL
LREC 2016
LREC 2016, May 2016, Portoroz, Slovenia

International audience; This paper describes the process of creating a corpus annotated for concepts and semantic relations in the scientific domain. A part of the ACL Anthology Corpus was selected for annotation, but the annotation process itself is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e6e8eb09d33c778d0f65bdd47d0b817c
https://hal.archives-ouvertes.fr/hal-01360407

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání