Search Results for author: Marko Robnik-Šikonja

Found 34 papers, 15 papers with code

BERT meets Shapley: Extending SHAP Explanations to Transformer-based Classifiers

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.

Unsupervised Approach to Multilingual User Comments Summarization

1 code implementation EACL (Hackashop) 2021 Aleš Žagar, Marko Robnik-Šikonja

The research on the summarization of user comments is still in its infancy, and human-created summarization datasets are scarce, especially for less-resourced languages.

Extractive Summarization Sentence

Exploring Neural Language Models via Analysis of Local and Global Self-Attention Spaces

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.

Machine Translation Question Answering +4

Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies

no code implementations12 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.

Cross-Lingual Transfer Hate Speech Detection

One model to rule them all: ranking Slovene summarizers

no code implementations20 Jun 2023 Aleš Žagar, Marko Robnik-Šikonja

We propose a system that recommends the most suitable summarization model for a given text.

Text Summarization

Detection of depression on social networks using transformers and ensembles

1 code implementation9 May 2023 Ilija Tavchioski, Marko Robnik-Šikonja, Senja Pollak

As the impact of technology on our lives is increasing, we witness increased use of social media that became an essential tool not only for communication but also for sharing information with community about our thoughts and feelings.

Depression Detection Language Modelling +1

Feature construction using explanations of individual predictions

no code implementations23 Jan 2023 Boštjan Vouk, Matej Guid, Marko Robnik-Šikonja

Feature construction can contribute to comprehensibility and performance of machine learning models.

Attribute

Unified Question Answering in Slovene

1 code implementation16 Nov 2022 Katja Logar, Marko Robnik-Šikonja

Most approaches are developed for English, while less-resourced languages are much less researched.

Cross-Lingual Transfer Multiple-choice +1

Training dataset and dictionary sizes matter in BERT models: the case of Baltic languages

no code implementations20 Dec 2021 Matej Ulčar, Marko Robnik-Šikonja

To analyze the importance of focusing on a single language and the importance of a large training set, we compare created models with existing monolingual and multilingual BERT models for Estonian, Latvian, and Lithuanian.

Dependency Parsing named-entity-recognition +3

Extracting and filtering paraphrases by bridging natural language inference and paraphrasing

1 code implementation13 Nov 2021 Matej Klemen, Marko Robnik-Šikonja

We propose a novel methodology for the extraction of paraphrasing datasets from NLI datasets and cleaning existing paraphrasing datasets.

Natural Language Inference

Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles

2 code implementations20 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.

Classification Fake News Detection +4

Evaluation of contextual embeddings on less-resourced languages

no code implementations22 Jul 2021 Matej Ulčar, Aleš Žagar, Carlos S. Armendariz, Andraž Repar, Senja Pollak, Matthew Purver, Marko Robnik-Šikonja

The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives.

Dependency Parsing

Cross-lingual alignments of ELMo contextual embeddings

no code implementations30 Jun 2021 Matej Ulčar, Marko Robnik-Šikonja

Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for less-resourced languages.

Dependency Parsing named-entity-recognition +4

Cross-lingual Transfer of Abstractive Summarizer to Less-resource Language

no code implementations8 Dec 2020 Aleš Žagar, Marko Robnik-Šikonja

Automatic evaluation shows that the summaries of our best cross-lingual model are useful and of quality similar to the model trained only in the target language.

Abstractive Text Summarization Cross-Lingual Transfer +2

MICE: Mining Idioms with Contextual Embeddings

1 code implementation13 Aug 2020 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.

Cross-Lingual Transfer Word Embeddings

FinEst BERT and CroSloEngual BERT: less is more in multilingual models

no code implementations14 Jun 2020 Matej Ulčar, Marko Robnik-Šikonja

Large pretrained masked language models have become state-of-the-art solutions for many NLP problems.

Dependency Parsing NER +3

Propositionalization and Embeddings: Two Sides of the Same Coin

2 code implementations8 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.

Relational Reasoning Vocal Bursts Valence Prediction

AttViz: Online exploration of self-attention for transparent neural language modeling

1 code implementation12 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.

Language Modelling text-classification +2

High Quality ELMo Embeddings for Seven Less-Resourced Languages

no code implementations22 Nov 2019 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.

NER text-classification +2

Generating Data using Monte Carlo Dropout

1 code implementation12 Sep 2019 Kristian Miok, Dong Nguyen-Doan, Daniela Zaharie, Marko Robnik-Šikonja

In many such cases, generators of synthetic data with the same statistical and predictive properties as the actual data allow efficient simulations and development of tools and applications.

Identifying roles of clinical pharmacy with survey evaluation

no code implementations17 Jun 2014 Andreja Čufar, Aleš Mrhar, Marko Robnik-Šikonja

Next, we build a model for predicting a successful introduction of clinical pharmacy to the clinical departments.

Attribute Decision Making +1

Data Generators for Learning Systems Based on RBF Networks

no code implementations28 Mar 2014 Marko Robnik-Šikonja

The proposed generator is based on RBF networks, which learn sets of Gaussian kernels.

Cannot find the paper you are looking for? You can Submit a new open access paper.