no code implementations • ACL 2019 • {\v{Z}}eljko Agi{\'c}, Ivan Vuli{\'c}
Viable cross-lingual transfer critically depends on the availability of parallel texts.
no code implementations • WS 2018 • Jan Vium Enghoff, S{\o}ren Harrison, {\v{Z}}eljko Agi{\'c}
Projecting linguistic annotations through word alignments is one of the most prevalent approaches to cross-lingual transfer learning.
no code implementations • WS 2018 • Alonso Vasquez, Renzo Ego Aguirre, C Angulo, y, John Miller, Claudia Villanueva, {\v{Z}}eljko Agi{\'c}, Roberto Zariquiey, Arturo Oncevay
We present an initial version of the Universal Dependencies (UD) treebank for Shipibo-Konibo, the first South American, Amazonian, Panoan and Peruvian language with a resource built under UD.
no code implementations • ACL 2017 • {\v{Z}}eljko Agi{\'c}, Natalie Schluter
In dependency parsing, jackknifing taggers is indiscriminately used as a simple adaptation strategy.
no code implementations • EACL 2017 • {\v{Z}}eljko Agi{\'c}, Barbara Plank, Anders S{\o}gaard
We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data.
no code implementations • WS 2017 • Tanja Samard{\v{z}}i{\'c}, Mirjana Starovi{\'c}, {\v{Z}}eljko Agi{\'c}, Nikola Ljube{\v{s}}i{\'c}
The paper documents the procedure of building a new Universal Dependencies (UDv2) treebank for Serbian starting from an existing Croatian UDv1 treebank and taking into account the other Slavic UD annotation guidelines.
no code implementations • LREC 2016 • Nikola Ljube{\v{s}}i{\'c}, Filip Klubi{\v{c}}ka, {\v{Z}}eljko Agi{\'c}, Ivo-Pavao Jazbec
In this paper we present newly developed inflectional lexcions and manually annotated corpora of Croatian and Serbian.
no code implementations • TACL 2016 • {\v{Z}}eljko Agi{\'c}, Anders Johannsen, Barbara Plank, H{\'e}ctor Mart{\'\i}nez Alonso, Natalie Schluter, Anders S{\o}gaard
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages.
no code implementations • LREC 2014 • Llu{\'\i}s Padr{\'o}, {\v{Z}}eljko Agi{\'c}, Xavier Carreras, Blaz Fortuna, Esteban Garc{\'\i}a-Cuesta, Zhixing Li, Tadej {\v{S}}tajner, Marko Tadi{\'c}
This paper presents the linguistic analysis tools and its infrastructure developed within the XLike project.
no code implementations • LREC 2014 • {\v{Z}}eljko Agi{\'c}, Nikola Ljube{\v{s}}i{\'c}
We build and evaluate statistical models for lemmatization, morphosyntactic tagging, named entity recognition and dependency parsing on top of SETimes. HR and the test sets, providing the state of the art in all the tasks.
no code implementations • LREC 2014 • {\v{Z}}eljko Agi{\'c}, Da{\v{s}}a Berovi{\'c}, Danijela Merkler, Marko Tadi{\'c}
Introducing the new annotation to Croatian Dependency Treebank, we also modify head attachment rules addressing subordinate conjunctions and subordinate clause predicates.
no code implementations • LREC 2012 • Da{\v{s}}a Berovi{\'c}, {\v{Z}}eljko Agi{\'c}, Marko Tadi{\'c}
We present the current state of development of the Croatian Dependency Treebank ― with special empahsis on adapting the Prague Dependency Treebank formalism to Croatian language specifics ― and illustrate its possible applications in an experiment with dependency parsing using MaltParser.