Cross-lingual Event-centric Open Analytics Research Academy

Risultati finali

Cross-lingual alignment, validation, contextualisation and OEKG (V2)

This report includes 1 A report on the crosslingual alignment validation and contextualisation methods developed in WP4 V22 A release of the corresponding software components V23 A report on The Open Event Knowledge Graph V2 released at MS4

Event-centric cross-lingual analytics, cross-cultural studies and CKPP (V2)

A report including information regarding 1 The methods for eventcentric crosslingual analytics developed in WP6 V22 The crosscultural studies conducted in WP6 V23 A release of the corresponding software components V24 A report on the Cleopatra Knowledge Processing Pipeline V2 released at MS5

Interactive access to multilingual information and hybrid computation (V2)

A report on the methods for interactive access to multilingual information and hybrid computation over crosslingual data developed in WP5 V2

Website published

Project homepage is online.

Pubblicazioni

Check_square at CheckThat! 2020: Claim Detection in Social Media via Fusion of Transformer and Syntactic Features

Autori: Gullal S. Cheema, Sherzod Hakimov, Ralph Ewerth
Pubblicato in: Proceedings of 11th International Conference of the CLEF Association, CLEF 2020, 2020
Editore: CEUR

EveOut: Reproducible Event Dataset for Studying andAnalyzing the Complex Event-Outlet Relationship

Autori: Swati, Tomaž Erjavec, Dunja Mladenić
Pubblicato in: SiKDD 2020, Numero Vol C, 2020, Pagina/e 17-20, ISBN 978-961-264-192-4
Editore: JSI

Croatian Film Review Dataset (Cro-FiReDa): A Sentiment Annotated Dataset of Film Reviews

Autori: G. Thakkar, N. Mikelić Preradović, M. Tadić
Pubblicato in: Slavic NLP 2023 The 9th Workshop on Slavic Natural Language Processing, 2023, Pagina/e 25, ISBN 978-1-959429-57-9
Editore: Association for Computational Linguistics
DOI: 10.48550/arxiv.2305.08173

CroSentiNews 2.0: A Sentence-Level News Sentiment Corpus

Autori: G. Thakkar, N. Mikelić Preradović, M. Tadić
Pubblicato in: 10th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, 2023, Pagina/e 94
Editore: Wydawnictwo Naukowe UAM
DOI: 10.48550/arxiv.2305.08187

User Access Models to Event-Centric Information

Autori: Sara Abdollahi
Pubblicato in: Companion Proceedings of the Web Conference 2022, 2022, Pagina/e 329–333
Editore: Association for Computing Machinery
DOI: 10.1145/3487553.3524193

Building and Evaluating Universal Named-Entity Recognition English corpus

Autori: Diego Alves, Gaurish Thakkar, Marko Tadić
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2021 co-located with TheWebConf, Numero vol 2829, 2021, Pagina/e 2-16
Editore: CEUR

A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods

Autori: Gullal S. Cheema, Sherzod Hakimov, Eric Müller-Budack, Ralph Ewerth
Pubblicato in: Workshop on Multi-ModalPre-Training for Multimedia Understanding (MMPT 2021), 2021
Editore: ACM
DOI: 10.1145/3463945.3469058

MLM - A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities

Autori: Jason Armitage, Endri Kacupaj, Golsa Tahmasebzadeh, Swati, Maria Maleshkova, Ralph Ewerth, Jens Lehmann
Pubblicato in: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020, Pagina/e 2967-2974, ISBN 9781450368599
Editore: ACM
DOI: 10.1145/3340531.3412783

Comprehensive Event Representations using Event Knowledge Graphs and Natural Language Processing

Autori: Tin Kuculo
Pubblicato in: 2022, ISBN 978-1-4503-9130-6
Editore: Association for Computing Machinery
DOI: 10.1145/3487553.3524199

Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-Resourced Languages

Autori: Diego Alves, Gaurish Thakkar, Marko Tadić
Pubblicato in: LREC2020 SLTU-CCURL Workshop, 2020, Pagina/e 153-158, ISBN 979-10-95546-35-1
Editore: ELRA
DOI: 10.6084/m9.figshare.13142756.v1

QuoteKG: A Multilingual Knowledge Graph of Quotes

Autori: Tin Kuculo, Simon Gottschalk, Elena Demidova
Pubblicato in: Lecture Notes in Computer Science, 2022, ISBN 978-3-031-06980-2
Editore: Springer
DOI: 10.1007/978-3-031-06981-9_21

Multi-task Learning for Cross-Lingual Sentiment Analysis

Autori: Gaurish Thakkar, Nives Mikelić Preradović, Marko Tadić
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2021 co-located with TheWebConf, Numero vol 2829, 2021, Pagina/e 76-84
Editore: CEUR

Typological Approach to Improve Dependency Parsing for Croatian Language

Autori: Diego Alves, Božo Bekavac, Marko Tadić
Pubblicato in: Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021), 2021, Pagina/e 1-11
Editore: Association for Computational Linguistics

Negation Detection Using NooJ

Autori: Gaurish Thakkar; Nives Mikelić Preradović;; Marko Tadić
Pubblicato in: 44th International Convention on Information, Communication and Electronic Technology (MIPRO), Numero 1, 2021, Pagina/e 263
Editore: IEEE
DOI: 10.23919/MIPRO52101.2021.9597013

A Dataset for Information Spreading over the News

Autori: Abdul Sittar, Dunja Mladenić, Tomaž Erjavec
Pubblicato in: SiKDD 2020, Numero vol c, 2020, Pagina/e 5-8, ISBN 978-961-264-192-4
Editore: JSI

Quotations, Coreference Resolution, and Sentiment Annotations in Croatian News Articles: An Exploratory Study

Autori: Jelena Sarajlić, Gaurish Thakkar, Diego Alves, Nives Mikelic Preradovic
Pubblicato in: Proceedings of the Conference on Digital Curation Technologies (Qurator 2021), Numero Vol 2836, 2021
Editore: CEUR

OEKG: The Open Event Knowledge Graph

Autori: Simon Gottschalk, Endri Kacupaj, Sara Abdollahi, Diego Alves, Gabriel Amaral, Elisavet Koutsiana, Tin Kuculo, Daniela Major, Caio Mello, Gullal S. Cheema, Abdul Sittar, Swati, Golsa Tahmasebzadeh and Gaurish Thakkar
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2021 co-located with TheWebConf, Numero vol 2829, 2021, Pagina/e 61-75
Editore: CEUR

Classification of Cross-cultural News Events

Autori: Abdul Sittar, Dunja Mladenić
Pubblicato in: SiKDD 2021, 2021
Editore: JSI

TIB's Visual Analytics Group at MediaEval '20: Detecting Fake News on Corona Virus and 5G Conspiracy

Autori: Cheema, Gullal S.; Hakimov, Sherzod; Ewerth, Ralph
Pubblicato in: Proceedings of MediaEval 2020 Workshop, Numero 11, 2020
Editore: CEUR
DOI: 10.48550/arxiv.2101.03529

Training Multimodal Systems for Classification with Multiple Objectives

Autori: Jason Armitage, Shramana Thakur, Rishi Tripathi, Maria Maleshkova and Jens Lehmann
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2020 co-located with ESWC, Numero vol 2611, 2020, Pagina/e 57-71
Editore: CEUR

Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

Autori: Joan Plepi, Endri Kacupaj, Kuldeep Singh, Harsh Thakka, Jens Lehmann
Pubblicato in: ESWC, 2021, Pagina/e 356--371
Editore: Springer
DOI: 10.1007/978-3-030-77385-4_21

TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes

Autori: Sherzod Hakimov, Gullal S. Cheema, Ralph Ewerth
Pubblicato in: SemEval Task 5 co-located with NAACL 2022, 2022
Editore: Association for Computational Linguistics

UNER: Universal Named-Entity Recognition Framework

Autori: Diego Fernando Válio Antunes Alves, Tin Kuculo, Gabriel Amaral, Gaurish Thakkar and Marko Tadic
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2020 co-located with ESWC, Numero vol 2611, 2020, Pagina/e 72-79
Editore: CEUR

MM-Claims: A Dataset for Multimodal Claim Detection in Social Media

Autori: Gullal S. Cheema, Sherzod Hakimov, Abdul Sittar, Eric Müller-Budack, Christian Otto, Ralph Ewerth
Pubblicato in: NAACL Findings, 2022
Editore: Association for Computational Linguistics

Multilingual Comparative Analysis of Deep-Learning Dependency Parsing Results Using Parallel Corpora

Autori: D. Alves, B. Bekavac, M. Tadić
Pubblicato in: Workshop on Building and Using Comparable Corpora (BUCC 2022) @LREC2022, 2022, Pagina/e 33-42
Editore: Association for Computational Linguistics

Improving Generalization for Multimodal Fake News Detection

Autori: Sahar Tahmasebi, Sherzod Hakimov, Ralph Ewerth, Eric Müller-Budack
Pubblicato in: ICMR 2023 - International Conference on Multimedia Retrieval, 2023, ISBN 979-8-4007-0178-8
Editore: ACM
DOI: 10.1145/3591106.3592230

Analysis of Corpus-based Word-Order Typological Methods

Autori: Diego Alves; Božo Bekavac; Daniel Zeman; Marko Tadić
Pubblicato in: Sixth Workshop on Universal Dependencies, Numero 20, 2023, Pagina/e 36-46
Editore: Association for Computational Linguistics
DOI: 10.5281/zenodo.7947920

EventKG+Click: A Dataset of Language-specific Event-centric User Interaction Traces

Autori: Sara Abdollahi, Simon Gottschalk and Elena Demidova
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2020 co-located with ESWC, Numero vol 2611, 2020, Pagina/e 32-42
Editore: CEUR

Understanding the Impact of Geographical Bias on NewsSentiment: A Case Study on London and Rio Olympics

Autori: Swati, Dunja Mladenić
Pubblicato in: SiKDD 2021, 2021
Editore: JSI

On the Role of Images for Analyzing Claims in Social Media

Autori: Cheema, Gullal S.; Hakimov, Sherzod; Müller-Budack, Eric; Ewerth, Ralph
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2021 co-located with TheWebConf, Numero vol 2829, 2021, Pagina/e 32-46
Editore: CEUR

A Feature Analysis for Multimodal News Retrieval

Autori: Golsa Tahmasebzadeh, Sherzod Hakimov, Eric Müller-Budack and Ralph Ewerth
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2020 co-located with ESWC, Numero vol 2611, 2020, Pagina/e 43-56
Editore: CEUR

Evaluating Language Tools for Fifteen EU-official Under-resourced Languages

Autori: Diego Alves, Gaurish Thakkar, Marko Tadić
Pubblicato in: LREC2020, 2020, Pagina/e 1859-1866
Editore: ELRA
DOI: 10.6084/m9.figshare.13142747.v1

GeoWINE: Geolocation based Wiki, Image, News and Event Retrieval

Autori: Golsa Tahmasebzadeh; Endri Kacupaj; Eric Müller-Budack; Sherzod Hakimov; Jens Lehmann; Ralph Ewerth
Pubblicato in: SIGIR, Numero 7, 2021
Editore: ACM
DOI: 10.1145/3404835.3462786

Corpus-based Syntactic Typological Methods for Dependency Parsing Improvement

Autori: D. Alves, B. Bekavac, D. Zeman, M. Tadić
Pubblicato in: 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP (SIGTYP 2023), 2023, Pagina/e 76-88
Editore: Association for Computational Linguistics

"""Using the profile of publishers to predict barriers across news articles"""

Autori: Abdul Sittar, Dunja Mladenić
Pubblicato in: CEUR Workshop Proceedings, CLEOPATRA Workshop 2021 co-located with TheWebConf, Numero vol 2829, 2021
Editore: CEUR

Are You Following the Right News-Outlet? A MachineLearning based approach to outlet prediction

Autori: Swati, Dunja Mladenić
Pubblicato in: SiKDD 2020, Numero vol c, 2020, Pagina/e 33-36, ISBN 978-961-264-192-4
Editore: JSI

MM-Locate-News: Multimodal Focus Location Estimation in News

Autori: Golsa Tahmasebzadeh, Eric Müller-Budack, Sherzod Hakimov, Ralph Ewerth
Pubblicato in: MMM 2023 - International Conference on MultiMedia Modeling, Numero 2023, 2023, Pagina/e 204-216
Editore: Springer
DOI: 10.1007/978-3-031-27077-2_16

Multimodal Geolocation Estimation of News Photos

Autori: Golsa Tahmasebzadeh, Sherzod Hakimov, Ralph Ewerth, Eric Müller-Budack
Pubblicato in: ECIR 2023 - European Conference on Information Retrieval, 2023, Pagina/e 204–220, ISBN 978-3-031-27077-2
Editore: Springer
DOI: 10.1007/978-3-031-28238-6_14

The Optimization of Portuguese Named-Entity Recognition and Classification by Combining Local Grammars and Conditional Random Fields Trained with a Parsed Corpus

Autori: Diego Alves; Božo Bekavac; Marko Tadić
Pubblicato in: NooJ2020 conference, Numero vol 1389, 2021, Pagina/e 196-205
Editore: Springer
DOI: 10.1007/978-3-030-70629-6_17

Building Multilingual Corpora for a Complex Named Entity Recognition and Classification Hierarchy using Wikipedia and DBpedia

Autori: Diego Alves, Gaurish Thakkar, Gabriel Amaral, Tin Kuculo, Marko Tadić
Pubblicato in: Proceedings of the Conference on Digital Curation Technologies (Qurator 2021), Numero Vol 2836, 2021
Editore: CEUR

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

Autori: Endri Kacupaj, Barshana Banerjee, Kuldeep Singh, Jens Lehmann
Pubblicato in: ESWC, 2021, Pagina/e 598-613
Editore: Springer
DOI: 10.1007/978-3-030-77385-4_36

Data Augmentation for Pipeline-Based Speech Translation

Autori: Diego Alves, Askars Salimbajevs, Mārcis Pinnis
Pubblicato in: Human Language Technologies – The Baltic Perspective - Proceedings of the Ninth International Conference Baltic HLT 2020, 2020, Pagina/e 73-79, ISBN 9781643681160
Editore: IOS Press
DOI: 10.3233/faia200605

VQuAnDa: Verbalization QUestion ANswering DAtaset

Autori: Endri Kacupaj, Hamid Zafar, Jens Lehmann, Maria Maleshkova
Pubblicato in: The Semantic Web - 17th International Conference, ESWC 2020, Heraklion, Crete, Greece, May 31–June 4, 2020, Proceedings, Numero 12123, 2020, Pagina/e 531-547, ISBN 978-3-030-49460-5
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-49461-2_31

Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets

Autori: Gaurish Thakkar, Mārcis Pinnis
Pubblicato in: Human Language Technologies – The Baltic Perspective - Proceedings of the Ninth International Conference Baltic HLT 2020, 2020, Pagina/e 55 - 61, ISBN 9781643681160
Editore: IOS Press
DOI: 10.3233/faia200602

EveOut: an Event-centric News Dataset to Analyze an Outlet’s Event Selection

Autori: - Swati, Dunja Mladenić and Tomaž Erjavec
Pubblicato in: Informatica - Slovenia, Numero Vol. 45, No. 7, 2021, Pagina/e 25-30, ISSN 0350-5596
Editore: Slovensko Drustvo Informatika
DOI: 10.31449/inf.v45i7.3410

Combining sentiment analysis classifiers to explore multilingual news articles covering London 2012 and Rio 2016 Olympics

Autori: Caio Mello, Gullal S. Cheema, Gaurish Thakkar
Pubblicato in: International Journal of Digital Humanities, 2022, ISSN 2524-7840
Editore: Springer
DOI: 10.1007/s42803-022-00052-9

LaSER: Language-specific event recommendation

Autori: Sara Abdollahi, Simon Gottschalk, Elena Demidova
Pubblicato in: Journal of Web Semantics, Numero 15708268, 2022, ISSN 1570-8268
Editore: Elsevier BV
DOI: 10.1016/j.websem.2022.100759

Assessing the Quality of Sources in Wikidata Across Languages: A Hybrid Approach

Autori: Gabriel Amaral, Alessandro Piscopo, Lucie-Aimée Kaffee, Odinaldo Rodrigues, Elena Simperl
Pubblicato in: Journal of Data and Information Quality, Numero 19361955, 2021, Pagina/e 1–35, ISSN 1936-1955
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3484828

Political and Economic Patterns in COVID-19 News: From Lockdown to Vaccination

Autori: Abdul Sittar, Dunja Mladenić, Marko Grobelnik
Pubblicato in: IEEE Access, Numero 21693536, 2022, Pagina/e 40036-40050, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2022.3164692

Analysis of information cascading and propagation barriers across distinctive news events

Autori: Abdul Sittar; Dunja Mladenic; Marko Grobelnik
Pubblicato in: Journal of Intelligent Information Systems, Numero 58, 2021, Pagina/e 119–152, ISSN 1573-7675
Editore: Springer
DOI: 10.48550/arxiv.2212.07742

Risultati finali

Pubblicazioni

Condividi questa pagina

Scarica