publications

2023

1. EACL

   Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages

   Nikola Ivačič, Thi Hong Hanh Tran, Boshko Koloski, and 2 more authors

   In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), 2023

   Bib

   @inproceedings{ivavcivc2023analysis,
     title = {Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages},
     author = {Iva{\v{c}}i{\v{c}}, Nikola and Tran, Thi Hong Hanh and Koloski, Boshko and Pollak, Senja and Purver, Matthew},
     booktitle = {Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)},
     pages = {106--112},
     year = {2023}
   }

2. ICLR

   Inducing Document Representations from Graphs: A Blueprint

   Boshko Koloski, Marko Pranjic, Nada Lavrac, and 2 more authors

   2023

   Bib

   @article{koloski2023inducing,
     title = {Inducing Document Representations from Graphs: A Blueprint},
     author = {Koloski, Boshko and Pranjic, Marko and Lavrac, Nada and {\v{S}}krlj, Bla{\v{z}} and Pollak, Senja},
     year = {2023}
   }

2022

1. DiscoveryScience

   Retrieval-efficiency trade-off of Unsupervised Keyword Extraction

   Blaž Škrlj, Boshko Koloski, and Senja Pollak

   In Discovery Science: 25th International Conference, DS 2022, Montpellier, France, October 10–12, 2022, Proceedings, 2022

   Bib

   @inproceedings{vskrlj2022retrieval,
     title = {Retrieval-efficiency trade-off of Unsupervised Keyword Extraction},
     author = {{\v{S}}krlj, Bla{\v{z}} and Koloski, Boshko and Pollak, Senja},
     booktitle = {Discovery Science: 25th International Conference, DS 2022, Montpellier, France, October 10--12, 2022, Proceedings},
     pages = {379--393},
     year = {2022},
     organization = {Springer}
   }

2. Neurocomputing

   Knowledge graph informed fake news classification via heterogeneous representation ensembles

   Boshko Koloski, Timen Stepišnik Perdih, Marko Robnik-Šikonja, and 2 more authors

   Neurocomputing, 2022

   Abs Bib

   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. An emerging problem in the modern era is fake news detection—many easily available pieces of information are not necessarily factually correct, and can lead to wrong conclusions or are used for manipulation. In this work we explore how different document representations, ranging from simple symbolic bag-of-words, to contextual, neural language model-based ones can be used for efficient fake news identification. One of the key contributions is a set of novel document representation learning methods based solely on knowledge graphs, i.e., extensive collections of (grounded) subject-predicate-object triplets. We demonstrate that knowledge graph-based representations already achieve competitive performance to conventionally accepted representation learners. Furthermore, when combined with existing, contextual representations, knowledge graph-based document representations can achieve state-of-the-art performance. To our knowledge this is the first larger-scale evaluation of how knowledge graph-based representations can be systematically incorporated into the process of fake news classification.

   @article{KOLOSKI2022208,
     title = {Knowledge graph informed fake news classification via heterogeneous representation ensembles},
     journal = {Neurocomputing},
     volume = {496},
     pages = {208-226},
     year = {2022},
     issn = {0925-2312},
     doi = {https://doi.org/10.1016/j.neucom.2022.01.096},
     url = {https://www.sciencedirect.com/science/article/pii/S0925231222001199},
     author = {Koloski, Boshko and {Stepišnik Perdih}, Timen and Robnik-Šikonja, Marko and Pollak, Senja and Škrlj, Blaž},
     keywords = {Fake news detection, Knowledge graphs, Text representation, Representation learning, Neuro-symbolic learning}
   }

3. ACL

   E8-IJS@ LT-EDI-ACL2022-BERT, AutoML and knowledge-graph backed detection of depression

   Ilija Tavchioski, Boshko Koloski, Blaž Škrlj, and 1 more author

   In Proceedings of the second workshop on language technology for equality, diversity and inclusion, 2022

   Bib

   @inproceedings{tavchioski2022e8,
     title = {E8-IJS@ LT-EDI-ACL2022-BERT, AutoML and knowledge-graph backed detection of depression},
     author = {Tavchioski, Ilija and Koloski, Boshko and {\v{S}}krlj, Bla{\v{z}} and Pollak, Senja},
     booktitle = {Proceedings of the second workshop on language technology for equality, diversity and inclusion},
     pages = {251--257},
     year = {2022}
   }

4. CLEF

   Early detection of depression with linear models using hand-crafted and contextual features

   Ilija Tavchioski, Blaž Škrlj, Senja Pollak, and 1 more author

   Working Notes of CLEF, 2022
5. LREC

   Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?

   Boshko Koloski, Senja Pollak, Blaž Škrlj, and 1 more author

   In Proceedings of the Thirteenth Language Resources and Evaluation Conference, Jun 2022

   Abs

   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 - supervised and ones that do not - unsupervised. In this study, we are interested in settings, where for a language under investigation, no training data is available. More specifically, we explore whether pretrained multilingual language models can be employed for zero-shot cross-lingual keyword extraction on low-resource languages with limited or no available labeled training data and whether they outperform state-of-the-art unsupervised keyword extractors. The comparison is conducted on six news article datasets covering two high-resource languages, English and Russian, and four low-resource languages, Croatian, Estonian, Latvian, and Slovenian. 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.

6. LREC

   Fusion of linguistic, neural and sentence-transformer features for improved term alignment

   Andraž Repar, Senja Pollak, Matej Ulčar, and 1 more author

   In Proceedings of the BUCC Workshop within LREC 2022, Jun 2022
7. EMNLP

   Knowledge informed sustainability detection from short financial texts

   Boshko Koloski, Syrielle Montariol, Matthew Purver, and 1 more author

   In Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP), Jun 2022
8. ACL

   EMBEDDIA at SemEval-2022 Task 8: Investigating Sentence, Image, and Knowledge Graph Representations for Multilingual News Article Similarity

   Elaine Zosa, Emanuela Boroş, Boshko Koloski, and 1 more author

   In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), Jun 2022

2021

1. EACL

   Interesting cross-border news discovery using cross-lingual article linking and document similarity

   Boshko Koloski, Elaine Zosa, Timen Stepišnik-Perdih, and 3 more authors

   In Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, Jun 2021

   Bib

   @inproceedings{koloski2021interesting,
     title = {Interesting cross-border news discovery using cross-lingual article linking and document similarity},
     author = {Koloski, Boshko and Zosa, Elaine and Stepi{\v{s}}nik-Perdih, Timen and {\v{S}}krlj, Bla{\v{z}} and Paju, Tarmo and Pollak, Senja},
     booktitle = {Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation},
     pages = {116--120},
     year = {2021}
   }

2. EACL

   Extending Neural Keyword Extraction with TF-IDF tagset matching

   Boshko Koloski, Senja Pollak, Blaž Škrlj, and 1 more author

   In Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, Apr 2021

   Abs

   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. In this work, we develop and evaluate our methods on four novel data sets covering less-represented, morphologically-rich languages in European news media industry (Croatian, Estonian, Latvian, and Russian). First, we perform evaluation of two supervised neural transformer-based methods, Transformer-based Neural Tagger for Keyword Identification (TNT-KID) and Bidirectional Encoder Representations from Transformers (BERT) with an additional Bidirectional Long Short-Term Memory Conditional Random Fields (BiLSTM CRF) classification head, and compare them to a baseline Term Frequency - Inverse Document Frequency (TF-IDF) based unsupervised approach. Next, we show that by combining the keywords retrieved by both neural transformer-based methods and extending the final set of keywords with an unsupervised TF-IDF based technique, we can drastically improve the recall of the system, making it appropriate for usage as a recommendation system in the media house environment.

3. AAAI

   Identification of COVID-19 related fake news via neural stacking

   Boshko Koloski, Timen Stepišnik-Perdih, Senja Pollak, and 1 more author

   In Combating Online Hostile Posts in Regional Languages during Emergency Situation: First International Workshop, CONSTRAINT 2021, Collocated with AAAI 2021, Virtual Event, February 8, 2021, Revised Selected Papers 1, Apr 2021

   Bib

   @inproceedings{koloski2021identification,
     title = {Identification of COVID-19 related fake news via neural stacking},
     author = {Koloski, Boshko and Stepi{\v{s}}nik-Perdih, Timen and Pollak, Senja and {\v{S}}krlj, Bla{\v{z}}},
     booktitle = {Combating Online Hostile Posts in Regional Languages during Emergency Situation: First International Workshop, CONSTRAINT 2021, Collocated with AAAI 2021, Virtual Event, February 8, 2021, Revised Selected Papers 1},
     pages = {177--188},
     year = {2021},
     organization = {Springer}
   }

4. EACL

   EMBEDDIA tools, datasets and challenges: Resources and hackathon contributions

   Senja Pollak, Marko Robnik-Šikonja, Matthew Purver, and 8 more authors

   In Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, Apr 2021

2020

1. CLEF

   Know your Neighbors: Efficient Author Profiling via Follower Tweets.

   Boshko Koloski, Senja Pollak, and Blaz Skrlj

   In CLEF (Working Notes), Apr 2020

   Bib

   @inproceedings{koloski2020know,
     title = {Know your Neighbors: Efficient Author Profiling via Follower Tweets.},
     author = {Koloski, Boshko and Pollak, Senja and Skrlj, Blaz},
     booktitle = {CLEF (Working Notes)},
     year = {2020}
   }

2. Knowledge graph-based document embedding enrichment

   Boshko Koloski

   Apr 2020

   Bib

   @article{koloski2020knowledge,
     title = {Knowledge graph-based document embedding enrichment},
     author = {Koloski, Boshko},
     year = {2020}
   }

3. CLEF

   Multilingual Detection of Fake News Spreaders via Sparse Matrix Factorization.

   Boshko Koloski, Senja Pollak, and Blaz Skrlj

   In CLEF (Working Notes), Apr 2020

   Bib

   @inproceedings{koloski2020multilingual,
     title = {Multilingual Detection of Fake News Spreaders via Sparse Matrix Factorization.},
     author = {Koloski, Boshko and Pollak, Senja and Skrlj, Blaz},
     booktitle = {CLEF (Working Notes)},
     year = {2020}
   }