no code implementations • LTEDI (ACL) 2022 • Ilija Tavchioski, Boshko Koloski, Blaž Škrlj, Senja Pollak
Depression is a mental illness that negatively affects a person’s well-being and can, if left untreated, lead to serious consequences such as suicide.
no code implementations • EACL (Hackashop) 2021 • Enja Kokalj, Blaž Škrlj, Nada Lavrač, Senja Pollak, Marko Robnik-Šikonja
Transformer-based neural networks offer very good classification performance across a wide range of domains, but do not provide explanations of their predictions.
no code implementations • EACL (Hackashop) 2021 • Boshko Koloski, Elaine Zosa, Timen Stepišnik-Perdih, Blaž Škrlj, Tarmo Paju, Senja Pollak
Team Name: team-8 Embeddia Tool: Cross-Lingual Document Retrieval Zosa et al. Dataset: Estonian and Latvian news datasets abstract: Contemporary news media face increasing amounts of available data that can be of use when prioritizing, selecting and discovering new news.
no code implementations • EACL (Hackashop) 2021 • Senja Pollak, Marko Robnik-Šikonja, Matthew Purver, Michele Boggia, Ravi Shekhar, Marko Pranjić, Salla Salmela, Ivar Krustok, Tarmo Paju, Carl-Gustav Linden, Leo Leppänen, Elaine Zosa, Matej Ulčar, Linda Freienthal, Silver Traat, Luis Adrián Cabrera-Diego, Matej Martinc, Nada Lavrač, Blaž Škrlj, Martin Žnidaršič, Andraž Pelicon, Boshko Koloski, Vid Podpečan, Janez Kranjc, Shane Sheehan, Emanuela Boros, Jose G. Moreno, Antoine Doucet, Hannu Toivonen
This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program.
1 code implementation • EACL (Hackashop) 2021 • Blaž Škrlj, Shane Sheehan, Nika Eržen, Marko Robnik-Šikonja, Saturnino Luz, Senja Pollak
Large pretrained language models using the transformer neural network architecture are becoming a dominant methodology for many natural language processing tasks, such as question answering, text classification, word sense disambiguation, text completion and machine translation.
no code implementations • EACL (Hackashop) 2021 • Andraž Pelicon, Ravi Shekhar, Matej Martinc, Blaž Škrlj, Matthew Purver, Senja Pollak
We present a system for zero-shot cross-lingual offensive language and hate speech classification.
no code implementations • FNP (LREC) 2022 • Timen Stepišnik-Perdih, Andraž Pelicon, Blaž Škrlj, Martin Žnidaršič, Igor Lončarski, Senja Pollak
Ontologies are increasingly used for machine reasoning over the last few years.
no code implementations • 25 Dec 2023 • Boshko Koloski, Nada Lavrač, Bojan Cestnik, Senja Pollak, Blaž Škrlj, Andrej Kastrin
Our system aims to reduce both the ratio of outlier topics to the total number of topics and the similarity between topic definitions.
no code implementations • 27 Sep 2023 • Boshko Koloski, Nada Lavrač, Senja Pollak, Blaž Škrlj
In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data.
no code implementations • 12 Sep 2023 • Boshko Koloski, Blaž Škrlj, Marko Robnik-Šikonja, Senja Pollak
As cross-lingual transfer strategies, we compare the intermediate-training (\textit{IT}) that uses each language sequentially and cross-lingual validation (\textit{CLV}) that uses a target language already in the validation phase of fine-tuning.
1 code implementation • 4 Sep 2023 • Blaž Škrlj, Blaž Mramor
The proposed approach's feasibility is demonstrated by speeding up the state-of-the-art AutoML system on a synthetic data set with no performance loss.
no code implementations • 4 Sep 2023 • Blaž Škrlj, Nir Ki-Tov, Lee Edelist, Natalia Silberstein, Hila Weisman-Zohar, Blaž Mramor, Davorin Kopič, Naama Ziporin
Real-world production systems often grapple with maintaining data quality in large-scale, dynamic streams.
no code implementations • 8 Feb 2023 • Jan Kralj, Blaž Škrlj, Živa Ramšak, Nada Lavrač, Kristina Gruden
Biological systems can be studied at multiple levels of information, including gene, protein, RNA and different interaction networks levels.
no code implementations • 29 Sep 2022 • Blaž Škrlj, Adi Schwartz, Jure Ferlež, Davorin Kopič, Naama Ziporin
The main idea underlying this paradigm considers an incrementally updated model of the relation between the hyperparameter space and the output (target) space; the data for this model are obtained by evaluating the main learning engine, which is, for example, a factorization machine-based model.
no code implementations • 15 Aug 2022 • Blaž Škrlj, Boshko Koloski, Senja Pollak
Efficiently identifying keyphrases that represent a given document is a challenging task.
no code implementations • LREC 2022 • Boshko Koloski, Senja Pollak, Blaž Škrlj, Matej Martinc
We find that the pretrained models fine-tuned on a multilingual corpus covering languages that do not appear in the test set (i. e. in a zero-shot setting), consistently outscore unsupervised models in all six languages.
1 code implementation • 25 Nov 2021 • Urh Primožič, Blaž Škrlj, Sašo Džeroski, Matej Petković
The need for learning from unlabeled data is increasing in contemporary machine learning.
1 code implementation • 23 Nov 2021 • Sebastian Mežnar, Matej Bevec, Nada Lavrač, Blaž Škrlj
The increasing amounts of semantic resources offer valuable storage of human knowledge; however, the probability of wrong entries increases with the increased size.
2 code implementations • 20 Oct 2021 • Boshko Koloski, Timen Stepišnik-Perdih, Marko Robnik-Šikonja, Senja Pollak, Blaž Škrlj
Increasing amounts of freely available data both in textual and relational form offers exploration of richer document representations, potentially improving the model performance and robustness.
no code implementations • 17 Oct 2021 • Blaž Škrlj, Marko Jukič, Nika Eržen, Senja Pollak, Nada Lavrač
The COVID-19 pandemic triggered a wave of novel scientific literature that is impossible to inspect and study in a reasonable time frame manually.
no code implementations • 14 Oct 2021 • Blaž Škrlj, Matej Petkovič
Contemporary natural language processing (NLP) revolves around learning from latent document representations, generated either implicitly by neural language models or explicitly by methods such as doc2vec or similar.
no code implementations • 29 Jun 2021 • Timen Stepišnik Perdih, Nada Lavrač, Blaž Škrlj
The derived semantic explanations are potentially more informative, as they describe the key attributes in the context of more general background knowledge, e. g., at the biological process level.
1 code implementation • 31 Mar 2021 • Sebastian Mežnar, Nada Lavrač, Blaž Škrlj
This work is one of the first to explore transferability of the learned representations for the task of node regression; we show there exist pairs of networks with similar structure between which the trained models can be transferred (zero-shot), and demonstrate their competitive performance.
1 code implementation • EACL (Hackashop) 2021 • Boshko Koloski, Senja Pollak, Blaž Škrlj, Matej Martinc
Keyword extraction is the task of identifying words (or multi-word expressions) that best describe a given document and serve in news portals to link articles of similar topics.
1 code implementation • 23 Jan 2021 • Blaž Škrlj, Sašo Džeroski, Nada Lavrač, Matej Petković
The utility of ReliefE for high-dimensional data sets is ensured by its implementation that utilizes sparse matrix algebraic operations.
Multi-Label Classification Vocal Bursts Intensity Prediction
no code implementations • 11 Jan 2021 • Boshko Koloski, Timen Stepišnik Perdih, Senja Pollak, Blaž Škrlj
Identification of Fake News plays a prominent role in the ongoing pandemic, impacting multiple aspects of day-to-day life.
no code implementations • 16 Dec 2020 • Sebastian Mežnar, Blaž Škrlj
The competition "Predicting Generalization in Deep Learning (PGDL)" aims to provide a platform for rigorous study of generalization of deep learning models and offer insight into the progress of understanding and explaining these models.
1 code implementation • 23 Nov 2020 • Matej Petković, Dragi Kocev, Blaž Škrlj, Sašo Džeroski
In this work, we propose two novel (groups of) methods for unsupervised feature ranking and selection.
1 code implementation • 8 Sep 2020 • Sebastian Mežnar, Nada Lavrač, Blaž Škrlj
Learning from complex real-life networks is a lively research area, with recent advances in learning information-rich, low-dimensional network node representations.
Ranked #17 on Node Classification on Coauthor CS
2 code implementations • 5 Aug 2020 • Matej Petković, Blaž Škrlj, Dragi Kocev, Nikola Simidjievski
In real-life, and in particular high-dimensional domains, where only a small percentage of the whole feature space might be relevant, a robust and confident feature ranking leads to interpretable findings as well as efficient computation and good predictive performance.
no code implementations • 30 Jul 2020 • Matej Martinc, Blaž Škrlj, Sergej Pirkmajer, Nada Lavrač, Bojan Cestnik, Martin Marzidovšek, Senja Pollak
The abundance of literature related to the widespread COVID-19 pandemic is beyond manual inspection of a single expert.
2 code implementations • 8 Jun 2020 • Nada Lavrač, Blaž Škrlj, Marko Robnik-Šikonja
This paper outlines some of the modern data processing techniques used in relational learning that enable data fusion from different input data types and formats into a single table data representation, focusing on the propositionalization and embedding data transformation approaches.
1 code implementation • 12 May 2020 • Blaž Škrlj, Nika Eržen, Shane Sheehan, Saturnino Luz, Marko Robnik-Šikonja, Senja Pollak
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation.
1 code implementation • 20 Mar 2020 • Matej Martinc, Blaž Škrlj, Senja Pollak
With growing amounts of available textual data, development of algorithms capable of automatic analysis, categorization and summarization of these data has become a necessity.
no code implementations • 11 Feb 2020 • Blaž Škrlj, Sašo Džeroski, Nada Lavrač, Matej Petkovič
Black-box neural network models are widely used in industry and science, yet are hard to understand and interpret.
no code implementations • 16 Sep 2019 • Kristian Miok, Dong Nguyen-Doan, Blaž Škrlj, Daniela Zaharie, Marko Robnik-Šikonja
As a result of social network popularity, in recent years, hate speech phenomenon has significantly increased.
1 code implementation • 17 Jul 2019 • Blaž Škrlj, Jan Kralj, Nada Lavrač
Mining complex data in the form of networks is of increasing interest in many scientific disciplines.
1 code implementation • 16 Jul 2019 • Blaž Škrlj, Senja Pollak
In our experiments, we employ eight different network topology metrics, and empirically showcase on a parallel corpus, how the methods can be used for modeling the relations between nine selected languages.
1 code implementation • 15 Jul 2019 • Blaž Škrlj, Andraž Repar, Senja Pollak
Keyword extraction is used for summarizing the content of a document and supports efficient document retrieval, and is as such an indispensable part of modern text-based systems.
1 code implementation • 11 Feb 2019 • Blaž Škrlj, Jan Kralj, Janez Konc, Marko Robnik-Šikonja, Nada Lavrač
Network node embedding is an active research subfield of complex network analysis.
1 code implementation • 1 Feb 2019 • Blaž Škrlj, Matej Martinc, Jan Kralj, Nada Lavrač, Senja Pollak
The use of background knowledge is largely unexploited in text classification tasks.