Search Results for author: Marko Tadi{\'c}

Found 12 papers, 0 papers with code

Building the Spanish-Croatian Parallel Corpus

no code implementations LREC 2020 Bojana Mikeleni{\'c}, Marko Tadi{\'c}

This limits the usability of the corpus for research of language units at sentence and lower language levels only.

POS Translation

Building the Macedonian-Croatian Parallel Corpus

no code implementations LREC 2016 Ines Cebovi{\'c}, Marko Tadi{\'c}

The mk-hr{\_}pcorp is a unidirectional (mk→hr) parallel corpus composed of synchronic fictional prose texts received already in digital form with over 500 Kw in each language.

Croatian Dependency Treebank 2.0: New Annotation Guidelines for Improved Parsing

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.

Dependency Parsing

RECSA: Resource for Evaluating Cross-lingual Semantic Annotation

no code implementations LREC 2014 Achim Rettinger, Lei Zhang, Da{\v{s}}a Berovi{\'c}, Danijela Merkler, Matea Sreba{\v{c}}i{\'c}, Marko Tadi{\'c}

To support this line of research we developed what we believe could serve as a gold standard Resource for Evaluating Cross-lingual Semantic Annotation (RECSA).

Machine Translation

CroDeriV: a new resource for processing Croatian morphology

no code implementations LREC 2014 Kre{\v{s}}imir {\v{S}}ojat, Matea Sreba{\v{c}}i{\'c}, Marko Tadi{\'c}, Tin Paveli{\'c}

Language data structured in this way was further used for the expansion of other language resources for Croatian, such as Croatian WordNet and the Croatian Morphological Lexicon.

14 Lemmatization +1

Generation of Verbal Stems in Derivationally Rich Language

no code implementations LREC 2012 Kre{\v{s}}imir {\v{S}}ojat, Nives Mikeli{\'c} Preradovi{\'c}, Marko Tadi{\'c}

The paper presents a procedure for generating prefixed verbs in Croatian comprising combinations of one, two or three prefixes.

Text Generation

Croatian Dependency Treebank: Recent Development and Initial Experiments

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.

Dependency Parsing Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.