Search Results - "Klubička, Filip"

Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification by Nedumpozhimana, Vasudevan, Klubička, Filip, Kelleher, John D

“…This article examines the basis of Natural Language Understanding of transformer based language models, such as BERT. It does this through a case study on…”
Get full text

Quantitative fine-grained human evaluation of machine translation systems: a case study on English to Croatian by Klubička, Filip, Toral, Antonio, Sánchez-Cartagena, Víctor M.

“…This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build…”
Get full text

Size Matters: The Impact of Training Size in Taxonomically-Enriched Word Embeddings by Maldonado, Alfredo, Klubička, Filip, Kelleher, John

“…Word embeddings trained on natural corpora (e.g., newspaper collections, Wikipedia or the Web) excel in capturing thematic similarity (“topical relatedness”)…”
Get full text

Crawl and crowd to bring machine translation to under-resourced languages by Toral, Antonio, Esplá-Gomis, Miquel, Klubička, Filip, Ljubešić, Nikola, Papavassiliou, Vassilis, Prokopidis, Prokopis, Rubino, Raphael, Way, Andy

“…We present a widely applicable methodology to bring machine translation (MT) to under-resourced languages in a cost-effective and rapid manner. Our proposal…”
Get full text

SHARING HIGH-QUALITY LANGUAGE RESOURCES IN THE LEGAL DOMAIN TO DEVELOP NEURAL MACHINE TRANSLATION FOR UNDER-RESOURCED EUROPEAN LANGUAGES by Bago, Petra, Castilho, Sheila, Celeste, Edoardo, Dunne, Jane, Gaspari, Federico, Gíslason, Níels Rúnar, Kåsen, Andre, Klubička, Filip, Kristmannsson, Gauti, McHugh, Helen, Moran, Róisín, Loinsigh, Órla Ní, Olsen, Jon Arild, Parra Escartín, Carla, Ramesh, Akshai, Resende, Natalia, Sheridan, Páraic, Way, Andy

“…This article reports some of the main achievements of the European Union-funded PRINCIPLE project in collecting high-quality language resources (LRs) in the…”
Get full text

Probing Taxonomic and Thematic Embeddings for Taxonomic Information by Klubička, Filip, Kelleher, John D

“…Modelling taxonomic and thematic relatedness is important for building AI with comprehensive natural language understanding. The goal of this paper is to learn…”
Get full text

Probing with Noise: Unpicking the Warp and Weft of Embeddings by Klubička, Filip, Kelleher, John D

“…Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue…”
Get full text

Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space by Klubička, Filip, Nedumpozhimana, Vasudevan, Kelleher, John D

“…The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose…”
Get full text

Examining a hate speech corpus for hate speech detection and popularity prediction by Klubička, Filip, Fernández, Raquel

“…In Proceedings of 4REAL Workshop 9-16 (2018) As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech…”
Get full text

Is it worth it? Budget-related evaluation metrics for model selection by Klubička, Filip, Salton, Giancarlo D, Kelleher, John D

“…Creating a linguistic resource is often done by using a machine learning model that filters the content that goes through to a human annotator, before going…”
Get full text

Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian by Klubička, Filip, Toral, Antonio, Sánchez-Cartagena, Víctor M

“…Machine Translation, pp 1-21, (2018), http://rdcu.be/GIkb This paper presents a quantitative fine-grained manual evaluation approach to comparing the…”
Get full text

Fine-grained human evaluation of neural versus phrase-based machine translation by Klubička, Filip, Toral, Antonio, Sánchez-Cartagena, Víctor M

“…The Prague Bulletin of Mathematical Linguistics No. 108, pp. 121-132 (2017) We compare three approaches to statistical machine translation (pure phrase-based,…”
Get full text

Queer In AI: A Case Study in Community-Led Participatory AI by QueerInAI, Organizers Of, :, Ovalle, Anaelia, Subramonian, Arjun, Singh, Ashwin, Voelcker, Claas, Sutherland, Danica J, Locatelli, Davide, Breznik, Eva, Klubička, Filip, Yuan, Hang, J, Hetvi, Zhang, Huan, Shriram, Jaidev, Lehman, Kruno, Soldaini, Luca, Sap, Maarten, Deisenroth, Marc Peter, Pacheco, Maria Leonor, Ryskina, Maria, Mundt, Martin, Agarwal, Milind, McLean, Nyx, Xu, Pan, Pranav, A, Korpan, Raj, Ray, Ruchira, Mathew, Sarah, Arora, Sarthak, John, ST, Anand, Tanvi, Agrawal, Vishakha, Agnew, William, Long, Yanan, Wang, Zijie J, Talat, Zeerak, Ghosh, Avijit, Dennler, Nathaniel, Noseworthy, Michael, Jha, Sharvani, Baylor, Emi, Joshi, Aditya, Bilenko, Natalia Y, McNamara, Andrew, Gontijo-Lopes, Raphael, Markham, Alex, Dǒng, Evyn, Kay, Jackie, Saraswat, Manu, Vytla, Nikhil, Stark, Luke

“…2023 ACM Conference on Fairness, Accountability, and Transparency We present Queer in AI as a case study for community-led participatory design in AI. We…”
Get full text

Collaborative development of a rule-based machine translator between Croatian and Serbian by Klubicka, Filip, Ramírez-Sánchez, Gema, Ljubesic, Nikola

“…This paper describes the development and current state of a bidirectional Croatian-Serbian machine translation system based on the open-source Apertium…”
Get full text

Dealing with Data Sparseness in SMT with Factored Models and Morphological Expansion: a Case Study on Croatian by Sánchez-Cartagena, Víctor M, Ljubesic, Nikola, Klubicka, Filip

“…This paper describes our experience using available linguistic resources for Croatian in order to address data sparseness when building an English-to-Croatian…”
Get full text

Semantic Relatedness and Taxonomic Word Embeddings by Kacmajor, Magdalena, Kelleher, John D, Klubicka, Filip, Maldonado, Alfredo

“…This paper connects a series of papers dealing with taxonomic word embeddings. It begins by noting that there are different types of semantic relatedness and…”
Get full text

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP by Belz, Anya, Thomson, Craig, Reiter, Ehud, Abercrombie, Gavin, Alonso-Moral, Jose M, Arvan, Mohammad, Braggaar, Anouck, Cieliebak, Mark, Clark, Elizabeth, van Deemter, Kees, Dinkar, Tanvi, Dušek, Ondřej, Eger, Steffen, Fang, Qixiang, Gao, Mingqi, Gatt, Albert, Gkatzia, Dimitra, González-Corbelle, Javier, Hovy, Dirk, Hürlimann, Manuela, Ito, Takumi, Kelleher, John D, Klubicka, Filip, Krahmer, Emiel, Lai, Huiyuan, van der Lee, Chris, Li, Yiru, Mahamood, Saad, Mieskes, Margot, van Miltenburg, Emiel, Mosteiro, Pablo, Nissim, Malvina, Parde, Natalie, Plátek, Ondřej, Rieser, Verena, Ruan, Jie, Tetreault, Joel, Toral, Antonio, Wan, Xiaojun, Wanner, Leo, Watson, Lewis, Yang, Diyi

“…We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human…”
Get full text