Filip Klubička


I am a PhD student at DIT School of Computer Science, funded by the ADAPT Centre. With a background in information science and linguistics, I am interested in exploring and modelling linguistic or social phenomena.
So let us talk about the elephant in the room.
We, as humans, know that this room does not actually contain an elephant, and that these words individually have a different meaning than when combined together. However, computers do not.
This is what my research is about - teaching computers to understand human language, to understand the meaning of words and word phrases like ’spill the beans’. Giving computers the ability to differentiate between sentences like ‘That was a piece of cake.’ and ‘Could you pass me a piece of cake?’, knowing that the meaning is drastically different in one and the other.
This can be useful in many areas - on a small scale, think of the autocorrect on your phones. On a larger scale, think of voice assistants like Siri or Alexa. And on a future scale, think of a fully realized artificial intelligence, that can speak and understand language just as any human would.
In my spare time, of which there is little, I fancy myself a geek, gamer, singer, runner, pun enthusiast and language lover. I'm ambitious, enthusiastic and quite ambivalent. Sometimes even cool. On a good day.

Computational Linguistics, Natural Langage Processing, Semantics, Machine Learning, Digital Humanities

Alfredo Maldonado, Filip Klubička. ADAPT at SemEval-2018 Task 9: Skip-Gram Word Embeddings for Unsupervised Hypernym Discovery in Specialised Corpora. In: Proceedings of SemEval-2018.
Filip Klubička, Raquel Fernandez. Examining a hate speech corpus for hate speech detection and popularity prediction. In: Proceedings of 4REAL Workshop. 2018.
Filip Klubička, Giancarlo D. Salton, John D. Kelleher. Is it worth it? Budget-related evaluation metrics for model selection. In: Proceedings of LREC2018. 2018.
Filip Klubička, Antonio Toral, Victor M. Sanchez-Cartagena. Quantitative Fine-grained Human Evaluation of Machine Translation Systems. Machine Translation Journal. 2018.
Filip Klubička, Antonio Toral, Victor M. Sanchez-Cartagena. Fine-grained Human Evaluation of Neural versus Phrase-Based Machine Translation. The Prague Bulletin of Mathematical Linguistics. 2017.
Maja Popović, Mihael Arcan and Filip Klubička. Language Related Issues for Machine Translation Beetween Closely Related South Slavic Languages. Third workshop for NLP for Similar Languages, Varieties and Dialects, Osaka, Japan. 2016.
Nikola Ljubešić, Tomaž Erjavec, Darja Fišer, Tanja Samardžić, Maja Miličević, Filip Klubička, Filip Petkovski. Easily accessible language technologies for Slovene, Croatian and Serbian. In: Proceedings of Language Technologies and Digital Humanities Conference, Ljubljana. 2016.
Antonio Toral, Miquel Espla-Gomis, Filip Klubička, Nikola Ljubešić, Vassilis Papavassiliou, Prokopis Prokopidis, Raphael Rubino, Andy Way. Crawl and crowd to bring machine translation to under-resourced languages. Language Resource and Evaluation Journal. 2016.
Victor Manuel Sanchez Cartagena, Nikola Ljubešić, Filip Klubička. Dealing with data sparseness in SMT with factored models and morphological expansion: A case study on Croatian. Baltic Journal of Modern Computing, 2016.
Filip Klubička, Gema Ramirez Sanchez, Nikola Ljubešić. Collaborative development of a rule-based machine translator between Croatian and Serbian. Baltic Journal of Modern Computing, 2016.
Filip Klubička. Hashtags as discourse markers in digital communication. Patchwork Student Journal, 2016.
Nikola Ljubešić, Miquel Esplà-Gomis, Sergio Ortiz-Rojas, Filip Klubička. Producing monolingual web corpora and bitext at the same time: SpiderLing and bitextor's love affair. Proceedings of LREC 2016.
Nikola Ljubešić, Filip Klubička, Željko Agić, Ivo-Pavao Jazbec. New inflectional lexicons for improved processing of Croatian and Serbian. In: Proceedings of LREC 2016.
Antonio Toral, Tommi Pirinen, Andy Way, Raphael Rubino, Gema Ramirez Sanchez, Sergio Ortiz Rojas, Victor M. Sanchez-Cartagena, Jorge Ferrandez-Tordera, Mikel L. Forcada, Miquel Espla-Gomis, Nikola Ljubešić, Filip Klubička, Prokopis Prokopidis, Vassilis Papavassiliou. Automatic Acquisition of Machine Translation Resources in the Abu-MaTran Project. Sociedad Española para el Procesamiento del Lenguaje Natural, 2015.
Nikola Ljubešić, Miquel Esplà-Gomis, Filip Klubička, Nives Mikelić Preradović. Predicting Inflectional Paradigms and Lemmata of Unknown Words for Semi automatic Expansion of Morphological Lexicons. In: Proceedings of Recent Advances in Natural Language Processing, Hissar, Bulgaria, 2015.
Mateusz Milan-Stanojević, Višnja Josipović Smojver, Filip Klubička and Renata Geld. Linguistic schizophrenia in Croatia: internationally intelligible ELF that does not 'sound good'. In: Proceedings of The 7th International Conference of English as a Lingua Franca, Athens, 2014.
Miquel Esplà-Gomis, Filip Klubička, Nikola Ljubešić, Sergio Ortiz-Rojas, Vassilis Papavassiliou and Prokopis Prokopidis. Comparing two acquisition systems for automatically building an English–Croatian parallel corpus from multilingual websites. In: Proceedings of LREC 2014.
Nikola Ljubešić and Filip Klubička. {bs,hr,sr}WaC - Web corpora of Bosnian, Croatian and Serbian. In: Proceedings of the 9th Web as Corpus Workshop. Association for Computational Linguistics, 2014.
Filip Klubička and Nikola Ljubešić. Using crowdsourcing in building a morphosyntactically annotated and lemmatized silver standard corpus of Croatian. In: Proceedings of the 9th Language Technologies Conference. Information Society - S 2014. 

Gave talk at 4REAL workshop, Miyazaki, Japan
Presented poster at LREC'18, Miyazaki, Japan
Presented poster at EAMT'16, Riga, Latvia
Presented two posters at LREC'16, Portorož, Slovenia

Dean's Award for Academic Excellence, Zagreb, Croatia, 2014
Rector's Award for Outstanding Research Project, Zagreb, Croatia, 2014
Rector's Award for Project of High Cultural Significance, Zagreb, Croatia, 2014

Google Scholar: