Me

I am currently a postdoctoral researcher at the Trustworthy Human Language Technologies Research Group, Ruhr University Bochum, working on Privacy-Preserving Natural Language Processing. I have previously worked as a postdoctoral researcher at the Research Group Data Mining and Machine Learning, University of Vienna, in the role of principal investigator on the project "Cognitive Plausibility of Deep Learning Language Models". I have also worked as a postdoctoral researcher at the Institute of Formal and Applied Linguistics, Charles University in Prague, conducting research on Text Summarization as part of the European Live Translator project.

My research interests include Differentially-Private Synthetic Text Generation and other applications of Deep Learning in Natural Language Processing, such as Sentiment Analysis, Topic Recognition, and Text Summarization. I conducted my PhD studies within the SoftEng Group at Politecnico di Torino university in Italy where I finished my thesis on Text-based Sentiment Analysis and Music Emotion Recogniton. I also worked in a collaborative project about On-Car Music Recommender Systems within JOL MobiLab of TIM.

News

Projects

Current

  • Language Impact of Differentially-Private Synthetic Text Generation - Postdoc Researcher @ Ruhr University Bochum
  • Cognitive Plausibility of Deep Learning Language Models - Coordinating Principal Investigator @ University of Vienna
  • Knowledge-Infused Deep Learning for Natural Language Processing - Postdoc Researcher @ University of Vienna

Past

  • European Live Translator - Postdoc Researcher @ UFAL, Charles University in Prague
  • On-Car Music Recommender Systems - PhD Student @ Politecnico di Torino, TIM

Resources

  • AlbSpellFix for cleaning corpora of Albanian texts GITHUB
  • AlbNews corpus for topic modeling in Albanian LINDAT
  • AlbNER corpus for named entity recognition in Albanian LINDAT
  • AlbMoRe movie reviews for sentiment analysis in Albanian LINDAT
  • OAGL paper metadata corpus for analysing paper lengths LINDAT
  • OAGT corpus of paper texts for topic recognition ZENODO
  • OAGSX title generation corpus for text summarization LINDAT
  • OAGKX keyword generation corpus for keyword analysis LINDAT

Students

  • Mirkan Albayrak
  • Emin Guliev

Publications

Books

  • Erion Çano, Edmond Tupja: Terma dhe koncepte nga inteligjenca artificiale. ISBN: 978-9928-807-34-2, Albas, Tiranë, nëntor 2023.
  • Erion Çano, Edmond Tupja: Fjalor i teknologjisë së informacionit, Botimi I. ISBN: 978-9928-371-35-5, Pegi, Tiranë, nëntor 2022.
  • Erion Çano, Edmond Tupja: Terminologji informatike: problematika dhe zgjidhje. ISBN: 978-9928-320-83-4, DOI: 10.5281/zenodo.6378930, Tiranë, mars 2022. Zenodo PDF EPUB MOBI
  • Erion Çano: Text-based Sentiment Analysis and Music Emotion Recognition. Ph.D. Thesis, Department of Control and Computer Engineering, Politecnico di Torino, Italy, 2018. WEB PDF

Papers

2024

  • Erion Çano, Dario Lamaj: AlbNews: A Corpus of Headlines for Topic Modeling in Albanian. ArXiv DATA
  • Matthias Aßenmacher, Andreas Stephan, Leonie Weissweiler, Erion Çano, Ingo Ziegler, Marwin Härttrich, Bernd Bischl, Benjamin Roth, Christian Heumann, Hinrich Schütze: Collaborative Development of Modular Open Source Educational Resources for Natural Language Processing. ACL

2023

  • Lukas Thoma, Ivonne Weyers, Erion Çano, Stefan Schweter, Jutta L Mueller, Benjamin Roth: CogMemLM: Human-Like Memory Mechanisms Improve Performance and Cognitive Plausibility of LLMs. ACL
  • Erion Çano: AlbNER: A Corpus for Named Entity Recognition in Albanian. ArXiv DATA
  • Vasiliki Kougia, Simon Fetzel, Thomas Kirchmair, Erion Çano, Sina Moayed Baharlou, Sahand Sharifzadeh, Benjamin Roth: MemeGraphs: Linking Memes to Knowledge Graphs. SPRINGER CODE
  • Erion Çano, Xhesilda Vogli: CSREU: A Novel Dataset about Corporate Social Responsibility and Performance Indicators. ArXiv DATA
  • Erion Çano: AlbMoRe: A Corpus of Movie Reviews for Sentiment Analysis in Albanian. ArXiv DATA CODE
  • Xhesilda Vogli, Erion Çano: CSRCZ: A Dataset About Corporate Social Responsibility in Czech Republic. ArXiv DATA CODE

2022

  • Amir Ziaee, Erion Çano: Batch Layer Normalization: A new normalization layer for CNNs and RNNs. ACM CODE
  • Erion Çano, Benjamin Roth: Topic Segmentation of Research Article Collections. ArXiv DATA
  • Stefan Schweter, Luisa März, Katharina Schmid, Erion Çano: hmBERT: Historical Multilingual Language Models for Named Entity Recognition. ArXiv CODE

2021

  • Benjamin Roth, Erion Çano: Focused Contrastive Training for Test-based Constituency Analysis. ArXiv NeurIPS

2020

  • Erion Çano, Ondřej Bojar: How Many Pages? Paper Length Prediction from the Metadata, In: NLPIR, Seoul, Korea. ACM DATA CODE
  • Erion Çano, Ondřej Bojar: Automating Text Naturalness Evaluation of NLG Systems. ArXiv
  • Erion Çano, Ondřej Bojar: Human or Machine: Automating Human Likeliness Evaluation of NLG Texts. ArXiv
  • Erion Çano, Ondřej Bojar: Two Huge Title and Keyword Generation Corpora of Research Articles, In: LREC, Marseille, France. ACL BibTeX DATA

2019

  • Erion Çano, Ondřej Bojar: Keyphrase Generation: A Multi-Aspect Survey, In: FRUCT, Helsinki, Finland. IEEE DATA
  • Erion Çano, Ondřej Bojar: Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study, In: INLG, Tokyo, Japan. ACL BibTeX DATA
  • Erion Çano, Ondřej Bojar: Keyphrase Generation: A Text Summarization Struggle, In: NAACL, Minneapolis, USA. ACL BibTeX DATA
  • Erion Çano, Ondřej Bojar: Sentiment Analysis of Czech Texts: An Algorithmic Survey, In: ICAART, Prague, Czechia. SCITEPRESS
  • Erion Çano, Maurizio Morisio: Word Embeddings for Sentiment Analysis: A Comprehensive Empirical Survey. ArXiv

2018

  • Erion Çano, Maurizio Morisio: A data-driven neural network architecture for sentiment analysis, In: Data Technologies and Applications (53) 1. EMERALD
  • Erion Çano, Maurizio Morisio: A Deep Learning Architecture for Sentiment Analysis, In: Geoinformatics and Data Analysis, Prague, Czechia. ACM
  • Erion Çano, Maurizio Morisio: Role of Data Properties on Sentiment Analysis of Texts via Convolutions, In: WorldCist, Naples, Italy. SPRINGER BibTeX

2017

  • Erion Çano, Maurizio Morisio: Quality of Word Embeddings on Sentiment Analysis Tasks, In: NLDB, Liege, Belgium. SPRINGER BibTeX DATA
  • Erion Çano, Maurizio Morisio: MoodyLyrics: A Sentiment Annotated Lyrics Dataset, In: ISMSI, Hong Kong. ACM DATA
  • Erion Çano, Maurizio Morisio: Hybrid Recommendations, Recommender Systems, Systematic Review, In: Intelligent Data Analysis (21) 6. IOSPRESS
  • Erion Çano, Maurizio Morisio: Music Mood Dataset Creation Based on Lastfm Tags, In: AIAP, Vienna, Austria. PDF DATA
  • Erion Çano, Maurizio Morisio: Crowdsourcing Emotions in Music Domain, In: Artificial Intelligence & Applications (8) 4. PDF DATA

2016

  • Erion Çano, Riccardo Coppola, Eleonora Gargiulo, Marco Marengo, Maurizio Morisio: Mood-based On-Car Music Recommendations, In: INISCOM, Leicester, UK. SPRINGER BibTeX

2015

  • Erion Çano, Maurizio Morisio: Characterization of Public Datasets for Recommender Systems, In: RTSI, Torino, Italy. IEEE