114 citations · 315 across the 19 of their papers we have counts for
21 papers
Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
Boshko Koloski, Blaž Škrlj, Marko Robnik-Šikonja +1
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-sh…
Feature construction using explanations of individual predictions
Boštjan Vouk, Matej Guid, Marko Robnik-Šikonja
Feature construction can contribute to comprehensibility and performance of machine learning models. Unfortunately, it usually requires exhaustive search in the attribute space or…
Better sampling in explanation methods can prevent dieselgate-like deception
Domen Vreš, Marko Robnik Šikonja
Machine learning models are used in many sensitive areas where besides predictive accuracy their comprehensibility is also important. Interpretability of prediction models is neces…
Enhancing deep neural networks with morphological information
Matej Klemen, Luka Krsnik, Marko Robnik-Šikonja
Deep learning approaches are superior in NLP due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM…
Bayesian Methods for Semi-supervised Text Annotation
Kristian Miok, Gregor Pirs, Marko Robnik-Sikonja
Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assig…
MICE: Mining Idioms with Contextual Embeddings
Tadej Škvorc, Polona Gantar, Marko Robnik-Šikonja
Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful method…
To BAN or not to BAN: Bayesian Attention Networks for Reliable Hate Speech Detection
Kristian Miok, Blaz Skrlj, Daniela Zaharie +1
Hate speech is an important problem in the management of user-generated content. To remove offensive content or ban misbehaving users, content moderators need reliable hate speech…
FinEst BERT and CroSloEngual BERT: less is more in multilingual models
Matej Ulčar, Marko Robnik-Šikonja
Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. The research has been mostly focused on English language, though. While massiv…
Propositionalization and Embeddings: Two Sides of the Same Coin
Nada Lavrač, Blaž Škrlj, Marko Robnik-Šikonja
Data preprocessing is an important component of machine learning pipelines, which requires ample time and resources. An integral part of preprocessing is data transformation into t…
Multiple Imputation for Biomedical Data using Monte Carlo Dropout Autoencoders
Kristian Miok, Dong Nguyen-Doan, Marko Robnik-Šikonja +1
Due to complex experimental settings, missing values are common in biomedical data. To handle this issue, many methods have been proposed, from ignoring incomplete instances to var…
AttViz: Online exploration of self-attention for transparent neural language modeling
Blaž Škrlj, Nika Eržen, Shane Sheehan +3
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised…
Cross-lingual Transfer of Sentiment Classifiers
Marko Robnik-Sikonja, Kristjan Reba, Igor Mozetic
Word embeddings represent words in a numeric space so that semantic relations between words are represented as distances and directions in the vector space. Cross-lingual word embe…
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context
Carlos Santos Armendariz, Matthew Purver, Matej Ulčar +5
State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists. Stand…
High Quality ELMo Embeddings for Seven Less-Resourced Languages
Matej Ulčar, Marko Robnik-Šikonja
Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer pre…
Multilingual Culture-Independent Word Analogy Datasets
Matej Ulčar, Kristiina Vaik, Jessica Lindström +2
In text processing, deep neural networks mostly use word embeddings as an input. Embeddings have to ensure that relations between words are reflected through distances in a high-di…
Generating Data using Monte Carlo Dropout
Kristian Miok, Dong Nguyen-Doan, Daniela Zaharie +1
For many analytical problems the challenge is to handle huge amounts of available data. However, there are data science application areas where collecting information is difficult…
Prediction Uncertainty Estimation for Hate Speech Classification
Kristian Miok, Dong Nguyen-Doan, Blaž Škrlj +2
As a result of social network popularity, in recent years, hate speech phenomenon has significantly increased. Due to its harmful effect on minority groups as well as on large comm…
Exploring the relations between net benefits of IT projects and CIOs' perception of quality of software development disciplines
Damjan Vavpotič, Marko Robnik-Šikonja, Tomaž Hovelja
Software development enterprises are under consistent pressure to improve their management techniques and development processes. These are comprised of several disciplines like req…
Supervised and Unsupervised Neural Approaches to Text Readability
Matej Martinc, Senja Pollak, Marko Robnik-Šikonja
We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language model…
Identifying roles of clinical pharmacy with survey evaluation
Andreja Čufar, Aleš Mrhar, Marko Robnik-Šikonja
The survey data sets are important sources of data and their successful exploitation is of key importance for informed policy-decision making. We present how a survey analysis appr…
Data Generators for Learning Systems Based on RBF Networks
Marko Robnik-Šikonja
There are plenty of problems where the data available is scarce and expensive. We propose a generator of semi-artificial data with similar properties to the original data which ena…