English WordNet Random Walk Pseudo-Corpora

no code implementations • LREC 2020 • Filip Klubi{\v{c}}ka, Alfredo Maldonado, Abhijit Mahalunkar, John Kelleher

Our WordNet taxonomic random walk implementation allows the exploration of different random walk hyperparameters and the generation of a variety of different pseudo-corpora.

Word Embeddings

ADAPT at SemEval-2018 Task 9: Skip-Gram Word Embeddings for Unsupervised Hypernym Discovery in Specialised Corpora

no code implementations • SEMEVAL 2018 • Alfredo Maldonado, Filip Klubi{\v{c}}ka

This paper describes a simple but competitive unsupervised system for hypernym discovery.

Hypernym Discovery Word Embeddings

Language Related Issues for Machine Translation between Closely Related South Slavic Languages

no code implementations • WS 2016 • Maja Popovi{\'c}, Mihael Ar{\v{c}}an, Filip Klubi{\v{c}}ka

This work explores the obstacles for machine translation systems between closely related South Slavic languages, namely Croatian, Serbian and Slovenian.

Machine Translation Translation

New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian

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.

LEMMA

Producing Monolingual and Parallel Web Corpora at the Same Time - SpiderLing and Bitextor's Love Affair

no code implementations • LREC 2016 • Nikola Ljube{\v{s}}i{\'c}, Miquel Espl{\`a}-Gomis, Antonio Toral, Sergio Ortiz Rojas, Filip Klubi{\v{c}}ka

This paper presents an approach for building large monolingual corpora and, at the same time, extracting parallel data by crawling the top-level domain of a given language of interest.

Dealing with Data Sparseness in SMT with Factured Models and Morphological Expansion: a Case Study on Croatian

no code implementations • WS 2016 • Victor M. S{\'a}nchez-Cartagena, Nikola Ljube{\v{s}}i{\'c}, Filip Klubi{\v{c}}ka

Machine Translation

Collaborative Development of a Rule-Based Machine Translator between Croatian and Serbian

no code implementations • WS 2016 • Filip Klubi{\v{c}}ka, Gema Ram{\'\i}rez-S{\'a}nchez, Nikola Ljube{\v{s}}i{\'c}

Machine Translation

Predicting Inflectional Paradigms and Lemmata of Unknown Words for Semi-automatic Expansion of Morphological Lexicons

no code implementations • RANLP 2015 • Nikola Ljube{\v{s}}i{\'c}, Miquel Espl{\`a}-Gomis, Filip Klubi{\v{c}}ka, Nives Mikeli{\'c} Preradovi{\'c}

Comparing two acquisition systems for automatically building an English---Croatian parallel corpus from multilingual websites

no code implementations • LREC 2014 • Miquel Espl{\`a}-Gomis, Filip Klubi{\v{c}}ka, Nikola Ljube{\v{s}}i{\'c}, Sergio Ortiz-Rojas, Vassilis Papavassiliou, Prokopis Prokopidis

We used both tools for crawling 21 multilingual websites from the tourism domain to build a domain-specific English―Croatian parallel corpus.

Information Retrieval Machine Translation +1

bs,hr,srWaC - Web Corpora of Bosnian, Croatian and Serbian

no code implementations • WS 2014 • Nikola Ljube{\v{s}}i{\'c}, Filip Klubi{\v{c}}ka

Language Identification Language Modelling