Search Results for author: Senja Pollak

Found 49 papers, 15 papers with code

EMBEDDIA project: Cross-Lingual Embeddings for Less- Represented Languages in European News Media

no code implementations EAMT 2022 Senja Pollak, Andraž Pelicon

EMBEDDIA project developed a range of resources and methods for less-resourced EU languages, focusing on applications for media industry, including keyword extraction, comment moderation and article generation.

Keyword Extraction

IJS at TextGraphs-16 Natural Language Premise Selection Task: Will Contextual Information Improve Natural Language Premise Selection?

no code implementations COLING (TextGraphs) 2022 Thi Hong Hanh Tran, Matej Martinc, Antoine Doucet, Senja Pollak

The results demonstrate that the contextual representation is better at capturing meaningful information despite not being pretrained in the mathematical background compared to the statistical approach (e. g., the TF-IDF) with a boost of around 3. 00% MAP@500.

Embeddings models for Buddhist Sanskrit

no code implementations LREC 2022 Ligeia Lugli, Matej Martinc, Andraž Pelicon, Senja Pollak

We release a novel corpus of Buddhist texts, a novel corpus of general Sanskrit and word similarity and word analogy datasets for intrinsic evaluation of Buddhist Sanskrit embeddings models.

Semantic Similarity Semantic Textual Similarity +2

Extracting and Analysing Metaphors in Migration Media Discourse: towards a Metaphor Annotation Scheme

1 code implementation LREC 2022 Ana Zwitter Vitez, Mojca Brglez, Marko Robnik Šikonja, Tadej Škvorc, Andreja Vezovnik, Senja Pollak

The study of metaphors in media discourse is an increasingly researched topic as media are an important shaper of social reality and metaphors are an indicator of how we think about certain issues through references to other things.

Transfer Learning

JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches

1 code implementation SemEval (NAACL) 2022 Thi Hong Hanh Tran, Matej Martinc, Matthew Purver, Senja Pollak

The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be a semantically matching word vector.

Reverse Dictionary Zero-Shot Learning

E8-IJS@LT-EDI-ACL2022 - BERT, AutoML and Knowledge-graph backed Detection of Depression

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.


Exploratory Analysis of News Sentiment Using Subgroup Discovery

no code implementations EACL (BSNLP) 2021 Anita Valmarska, Luis Adrián Cabrera-Diego, Elvys Linhares Pontes, Senja Pollak

In this study, we present an exploratory analysis of a Slovenian news corpus, in which we investigate the association between named entities and sentiment in the news.

named-entity-recognition Named Entity Recognition +1

EMBEDDIA hackathon report: Automatic sentiment and viewpoint analysis of Slovenian news corpus on the topic of LGBTIQ+

no code implementations EACL (Hackashop) 2021 Matej Martinc, Nina Perger, Andraž Pelicon, Matej Ulčar, Andreja Vezovnik, Senja Pollak

We conduct automatic sentiment and viewpoint analysis of the newly created Slovenian news corpus containing articles related to the topic of LGBTIQ+ by employing the state-of-the-art news sentiment classifier and a system for semantic change detection.

Change Detection

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

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.


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

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.

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

XAI in Computational Linguistics: Understanding Political Leanings in the Slovenian Parliament

1 code implementation8 May 2023 Bojan Evkoski, Senja Pollak

We develop both classical machine learning and transformer language models to predict the left- or right-leaning of parliamentarians based on their given speeches on the topic of migrants.


The Recent Advances in Automatic Term Extraction: A survey

no code implementations17 Jan 2023 Hanh Thi Hong Tran, Matej Martinc, Jaya Caporusso, Antoine Doucet, Senja Pollak

Automatic term extraction (ATE) is a Natural Language Processing (NLP) task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms.

Feature Engineering Information Retrieval +4

Ensembling Transformers for Cross-domain Automatic Term Extraction

no code implementations12 Dec 2022 Hanh Thi Hong Tran, Matej Martinc, Andraz Pelicon, Antoine Doucet, Senja Pollak

Automatic term extraction plays an essential role in domain language understanding and several natural language processing downstream tasks.

Term Extraction

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

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.

Keyword Extraction Pretrained Multilingual Language Models

Named entity recognition architecture combining contextual and global features

1 code implementation15 Dec 2021 Tran Thi Hong Hanh, Antoine Doucet, Nicolas Sidere, Jose G. Moreno, Senja Pollak

Named entity recognition (NER) is an information extraction technique that aims to locate and classify named entities (e. g., organizations, locations,...) within a document into predefined categories.

named-entity-recognition Named Entity Recognition +1

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

JSI at the FinSim-2 task: Ontology-Augmented Financial Concept Classification

no code implementations17 Jun 2021 Timen Stepišnik Perdih, Senja Pollak, Blaž \v{Skrlj}

The task is to design a system that can automatically classify concepts from the Financial domain into the most relevant hypernym concept in an external ontology - the Financial Industry Business Ontology.

Extending Neural Keyword Extraction with TF-IDF tagset matching

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.

Keyword Extraction

Identification of COVID-19 related Fake News via Neural Stacking

no code implementations11 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.

Fake News Detection General Classification

SemEval-2020 Task 3: Graded Word Similarity in Context

no code implementations SEMEVAL 2020 Carlos Santos Armendariz, Matthew Purver, Senja Pollak, Nikola Ljube{\v{s}}i{\'c}, Matej Ul{\v{c}}ar, Ivan Vuli{\'c}, Mohammad Taher Pilehvar

This paper presents the Graded Word Similarity in Context (GWSC) task which asked participants to predict the effects of context on human perception of similarity in English, Croatian, Slovene and Finnish.

Translation Word Similarity

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

The NetViz terminology visualization tool and the use cases in karstology domain modeling

no code implementations LREC 2020 Senja Pollak, Vid Podpe{\v{c}}an, Dragana Miljkovic, Uro{\v{s}} Stepi{\v{s}}nik, {\v{S}}pela Vintar

We showcase the usefulness of the tool on examples from the karstology domain, where in the first use case we visualize the domain knowledge as represented in a manually annotated corpus of domain definitions, while in the second use case we show the power of visualization for domain understanding by visualizing automatically extracted knowledge in the form of triplets extracted from the karstology domain corpus.

TNT-KID: Transformer-based Neural Tagger for Keyword Identification

1 code implementation20 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.

Keyword Extraction Language Modelling

Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift

no code implementations LREC 2020 Matej Martinc, Petra Kralj Novak, Senja Pollak

We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings.

Domain Adaptation

Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methods

no code implementations28 Aug 2019 Fasih Haider, Senja Pollak, Pierre Albert, Saturnino Luz

A machine learning model trained on a smaller feature set will reduce the memory and computational resources of an emotion recognition system which can result in lowering the barriers for use of health monitoring technology.

Emotion Recognition feature selection

Language comparison via network topology

1 code implementation16 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.

RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation

1 code implementation15 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.

Keyword Extraction Retrieval

Gender Profiling for Slovene Twitter communication: the Influence of Gender Marking, Content and Style

no code implementations WS 2017 Ben Verhoeven, Iza {\v{S}}krjanec, Senja Pollak

Inspired by the TwiSty corpus and experiments (Verhoeven et al., 2016), we employed the Janes corpus (Erjavec et al., 2016) and its gender annotations to perform gender classification experiments on Twitter text comparing a token-based and a lemma-based approach.

General Classification LEMMA +1

Irregularity Detection in Categorized Document Corpora

no code implementations LREC 2012 Borut Sluban, Senja Pollak, Roel Coesemans, Nada Lavra{\v{c}}

The paper presents an approach to extract irregularities in document corpora, where the documents originate from different sources and the analyst's interest is to find documents which are atypical for the given source.

Document Classification Outlier Detection +1

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