Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Koloski, Boshko"'
Autor:
Andrenšek, Luka, Koloski, Boshko, Pelicon, Andraž, Lavrač, Nada, Pollak, Senja, Purver, Matthew
We investigate zero-shot cross-lingual news sentiment detection, aiming to develop robust sentiment classifiers that can be deployed across multiple languages without target-language training data. We introduce novel evaluation datasets in several le
Externí odkaz:
http://arxiv.org/abs/2409.20054
Autor:
Bernárdez, Guillermo, Telyatnikov, Lev, Montagna, Marco, Baccini, Federica, Papillon, Mathilde, Ferriol-Galmés, Miquel, Hajij, Mustafa, Papamarkou, Theodore, Bucarelli, Maria Sofia, Zaghen, Olga, Mathe, Johan, Myers, Audun, Mahan, Scott, Lillemark, Hansen, Vadgama, Sharvaree, Bekkers, Erik, Doster, Tim, Emerson, Tegan, Kvinge, Henry, Agate, Katrina, Ahmed, Nesreen K, Bai, Pengfei, Banf, Michael, Battiloro, Claudio, Beketov, Maxim, Bogdan, Paul, Carrasco, Martin, Cavallo, Andrea, Choi, Yun Young, Dasoulas, George, Elphick, Matouš, Escalona, Giordan, Filipiak, Dominik, Fritze, Halley, Gebhart, Thomas, Gil-Sorribes, Manel, Goomanee, Salvish, Guallar, Victor, Imasheva, Liliya, Irimia, Andrei, Jin, Hongwei, Johnson, Graham, Kanakaris, Nikos, Koloski, Boshko, Kovač, Veljko, Lecha, Manuel, Lee, Minho, Leroy, Pierrick, Long, Theodore, Magai, German, Martinez, Alvaro, Masden, Marissa, Mežnar, Sebastian, Miquel-Oliver, Bertran, Molina, Alexis, Nikitin, Alexander, Nurisso, Marco, Piekenbrock, Matt, Qin, Yu, Rygiel, Patryk, Salatiello, Alessandro, Schattauer, Max, Snopov, Pavel, Suk, Julian, Sánchez, Valentina, Tec, Mauricio, Vaccarino, Francesco, Verhellen, Jonas, Wantiez, Frederic, Weers, Alexander, Zajec, Patrik, Škrlj, Blaž, Miolane, Nina
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM). The challenge focused on the problem
Externí odkaz:
http://arxiv.org/abs/2409.05211
Large semantic knowledge bases are grounded in factual knowledge. However, recent approaches to dense text representations (i.e. embeddings) do not efficiently exploit these resources. Dense and robust representations of documents are essential for e
Externí odkaz:
http://arxiv.org/abs/2408.09794
Autor:
Caporusso, Jaya, Hoogland, Damar, Brglez, Mojca, Koloski, Boshko, Purver, Matthew, Pollak, Senja
Dehumanisation involves the perception and or treatment of a social group's members as less than human. This phenomenon is rarely addressed with computational linguistic techniques. We adapt a recently proposed approach for English, making it easier
Externí odkaz:
http://arxiv.org/abs/2404.07036
Autor:
Montariol, Syrielle, Martinc, Matej, Pelicon, Andraž, Pollak, Senja, Koloski, Boshko, Lončarski, Igor, Valentinčič, Aljoša
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) information. This textual data can provide valuable weak signals, for exam
Externí odkaz:
http://arxiv.org/abs/2404.05281
In an era marked by a rapid increase in scientific publications, researchers grapple with the challenge of keeping pace with field-specific advances. We present the `AHAM' methodology and a metric that guides the domain-specific \textbf{adapt}ation o
Externí odkaz:
http://arxiv.org/abs/2312.15784
In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data. In this work, we address this limitation by providing an approach for inferring
Externí odkaz:
http://arxiv.org/abs/2309.15757
The cross-lingual transfer is a promising technique to solve tasks in less-resourced languages. In this empirical study, we compare two fine-tuning approaches combined with zero-shot and full-shot learning approaches for large language models in a cr
Externí odkaz:
http://arxiv.org/abs/2309.06089
Efficiently identifying keyphrases that represent a given document is a challenging task. In the last years, plethora of keyword detection approaches were proposed. These approaches can be based on statistical (frequency-based) properties of e.g., to
Externí odkaz:
http://arxiv.org/abs/2208.07262
Keyword extraction is the task of retrieving words that are essential to the content of a given document. Researchers proposed various approaches to tackle this problem. At the top-most level, approaches are divided into ones that require training -
Externí odkaz:
http://arxiv.org/abs/2202.06650