John Pavlopoulos

Curriculum Vitae — last updated September 2026. Also available as PDF, in English and Greek, or as a short version.

Assistant Professor of Machine Learning, Department of Informatics, Athens University of Economics and Business. Researcher at Archimedes, Athena Research Center, and affiliated with Stockholm University.

• E-mail: ipavlopoulos (or annis) at aueb dot gr
• Office: Antoniadou Wing, 3rd Floor (A308), Patision 76, Athens 104 34
• Phone: +30 210 82 03 133
• Web: ipavlopoulos.github.io; Google Scholar

Research interests

Machine learning for Natural Language Processing, with applications in the Social Sciences and Humanities, and in Healthcare. In particular: machine and deep learning for text and images; mining emotion and named entities from large collections; classification for early diagnosis or filtering; and natural language generation.

Education

• 2010–2014 — PhD in Natural Language Processing, “Aspect Based Sentiment Analysis”. Department of Informatics, Athens University of Economics and Business, Greece. Supervisor: Professor Ion Androutsopoulos.
• 2008–2009 — MSc in Artificial Intelligence, School of Informatics, University of Edinburgh, UK. Dissertation supervised by Professor Mirella Lapata.
• 2001–2007 — School of Applied Mathematics and Physical Sciences, National Technical University of Athens, Greece.

Academic and professional experience

• Athens University of Economics and Business, Department of Informatics — Assistant Professor of Machine Learning.
• Archimedes, Athena Research Center — Researcher.
• Stockholm University, Department of Computer and Systems Sciences — Senior Lecturer (fixed-term) in NLP and Data Science (2020–2021); Postdoctoral Researcher (2019–2020); currently affiliated.
• Ca’ Foscari University of Venice, Department of Humanities — Visiting Scholar in NLP at the Venice Centre for Digital and Public Humanities (2021–2022). Co-organised the HTREC academic challenge.
• Google Jigsaw — Research associate (from 2018).
• Cognitiv+ — Data Scientist (2018–2019). Layout and skew detection in images of legal documents; data annotation manager.
• Liquid Media / Straintek — Senior Researcher (2016–2018), leading the team developing APIs for multilingual abusive language detection; Postdoctoral Researcher (2015–2016).
• Hellenic Army — Software development (2014–2015).
• BioASQ — Research associate (2012–2014).

Teaching

Currently teaching Natural Language Processing (MSc in Digital Methods for the Humanities), Programming with Java (BSc), and Data Mining (BSc) at the Athens University of Economics and Business.

Previously: Practical Data Science (MS in Data Science, AUEB); Natural Language Processing (PhD course, Stockholm University); Visiting Lecturer in Data Science (Stockholm University).

Scholarships and awards

• Google Research Award for postdoctoral studies.
• Best paper, 27th International Conference on Discovery Science (2024).
• Best paper, 1st Workshop on Machine Learning for Ancient Languages (2024).
• PriceWaterhouseCoopers scholarship for postgraduate studies.
• Thomaidio Award for the best BSc thesis in the university.
• Ganioti-Papageorgi scholarship for undergraduate studies.
• Aglaias Koufodimou scholarship for undergraduate studies.

Service

Member of the editorial board of magazén, International Journal for Digital and Public Humanities. Member of the organising committee of the ML4AL ACL workshop and of the programme committee of the Abusive Language Workshop. Reviewer for NeurIPS, ACL, EMNLP, COLING and NAACL-HLT, and for journals including Natural Language Engineering and Data Mining and Knowledge Discovery.

Research projects

• AIRIS: Mechanism-informed multimodal generative AI for causal and dynamical modelling in biomedical research. Member of the Athena Research Center team. Funded by Horizon Europe (2026-2030).

• LLM3: Improving online discussions and deliberations with large language models. Funded by Archimedes/Athena RC (2024-2025).

• EFRA: AI-enabled food risk prevention. EU-funded project (2023-2026).

• Studying toxicity classifiers. Project funded by Google (unrestricted research support), Senior Researcher (2022-2023).

• Natural Language Processing for Digital Art History, Project Manager (2021-2022).

• Automatic grading and assessment of electronic exams, Senior Researcher (2021).

• Cost model development for the moderation of user posts on online platforms. Project with the Joint Research Center, European Commission, Principal Investigator (2020).

• EXTREMUM:Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources. Data Science Group, Department of Computer and System Sciences, Stockholm University; Researcher (2019/2020).

• ConvAI: Context-aware abusive language detection in online conversations. Google Research Award, Principal Investigator (2019).

• ML2P Filter: Machine learning to filter profanity. Google Digital News Initiative (DNI) project; Principal Investigator (2016-2018).

• BioASQ. FP7 ICT, Research Associate (2012-2014).

Invited talks and session coordination

• 16 September 2026 — Τεχνητή Νοημοσύνη στην Εκπαίδευση: τα μοντέλα ΤΝ, αντικαταστάτες ή βοηθοί; Talk (in Greek) at the 2nd Model Junior High School of Athens, on critical literacy for AI output, what it changes in assessment, and moving from user to co-designer of the tools. Slides; interactive exercises.

• 29 August 2026 — Machine Learning for the Humanities. At the 25th International Congress of Byzantine Studies, Vienna, in the roundtable “6.04 RT — AI and Byzantine Studies”. Program.

• 9 March 2026 — Learning to Align: Addressing Frequency Distribution Shifts. Research seminar, Department of Statistics, Athens University of Economics and Business. Seminar listing.

• 24 September 2025 — Explainable Foundation Models for Historical and Subjective Data. Keynote at AI-based Methods for the Humanities, BIFOLD, Einstein Center Digital Future, Berlin. Program.

• 4 July 2025 — Machine Learning for Ancient Languages: Applications to Byzantine Manuscripts. At “Artificial Intelligence: Hopes and Fears”, 44th Thessaloniki Book Festival. Program.

• 12 June 2025 — Learning to Adapt: Addressing Character Frequency Distribution Shifts in HTR. SCOOP: Source Codes of the Past, Institute for Advanced Study, Princeton. Program.

Session coordination

• 8 September 2026 — WG2: Document or Handwriting Classification. Co-coordinated the working group’s conclusions session with Maria Konstantinidou and Paraskevi Platanou at the 2nd SCOOP Exchange Meeting, University of Vienna (7–9 September 2026). Program; SCOOP network.

Thesis supervision

Chatzipapadopoulou Anna, 2025. “Ensemble Learning in Uncertainty Quantification for Multi-Label Prediction: From Theoretical Foundations to Medical Image Understanding”. MSc Thesis, Computer Science, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos (pdf).

Schoinaki Maria, 2025. “Improvements to the explanations of Ithaca’s chronological attributions of ancient Greek inscriptions”. BSc Thesis, Computer Science, Department of Informatics, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos and Yannis Assael (pdf).

Pantelidis Ippokratis, 2025. “Exploring Post-Training Techniques for Diagnostic Captioning”. BSc Thesis, Computer Science, Department of Informatics, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos (pdf).

Voulgarakis Dionysios, 2024. “Improving Fraud Detection in Online Banking”. MSc Thesis, Data Science, Athens University of Economics and Business (link).

Samprovalaki Marina, 2024. “Exploring Multimodal Large Language Models for Medical Image Captioning”. MSc Thesis, Computer Science, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos (pdf).

Tsirmpas Dimitris, 2024. “Mitigating Polarisation in Online Discussions Through Adaptive Moderation Techniques”. MSc Thesis, Data Science, Athens University of Economics and Business (pdf).

Chatzipapadopoulou Anna, 2024. “Enhanced Biomedical Image Tagging”. BSc Thesis, Informatics, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos (pdf).

Kaliosis Panagiotis, 2023. “Exploring Uni-modal, Multi-modal and Few-shot Deep Learning Methods for Diagnostic Captioning”. MSc Thesis, Computer Science, Athens University of Economics and Business. Co-supervised with Ion Androutsopoulos (pdf).

Barmpounis Epameinondas-Konstantinos, 2022. “Computational analysis of Greek Parliamentary Minutes of the period 1946-1947”. MSc Thesis, Digital Methods for the Humanities (link)

Peteinou Eleni, 2022. “Toxicity classification for the detection of ageism on social media”. MSc Thesis, Digital Methods for the Humanities (link)

Anagnostopoulos Theodore, 2021. “Toxicity detection on Greek tweets”. MSc Thesis, Data Science (link).

Papadatos Emmanouil, 2021. “Text classification to automatically detect hazards in foods from official announcements and social media”. MSc thesis, Data Science (link)

Liagkou Konstantina, 2021. “Brand cannibalisation”. MSc Thesis, Data Science (link).

Ormyliotou Georgia, 2021. “Brand-based sentiment analysis”. MSc Thesis, Data Science (link).

Jimenéz Enrique Javier Cobo and Rigobello Ronaldo Soares, 2021. “Explainability Techniques to Locate and Correct Grammatical Errors”, Degree project at the master level, Department of Computer and Systems Sciences, Stockholm University (pdf).

Sjöstedt Nadia, 2021. “Explaining the Predictions of Text Toxicity Classifiers”, Degree project at the master level, Department of Computer and Systems Sciences, Stockholm University (pdf).

Paparrigopoulou Asimina, 2021. “Chronological Attribution of Papyri Using Machine Learning”, MS Thesis, Digital Methods for The Humanities, Athens University of Economics and Business (pdf).

Xenos Alexandros, 2021. “Conversational Context in Toxicity Detection”, MSc Thesis, Computer Science, Department of Informatics, Athens University of Economics and Business (pdf).

Karatzas Vasilis, 2021. “Exploring Diagnostic Captioning Methods”, MSc Thesis, Department of Informatics, Computer Science, Athens University of Economics and Business (pdf)

Marina Thalassinou-Lislevand, 2020. “Emotion Classification on Greek Tweets“, MSc Thesis, Data Science (pdf).

Fasoi Maria, 2020. “Language Modelling for Authorship Attribution In Homeric Texts”, MSc Thesis, Digital Methods for the Humanities (slides).

Stroumbouli Eleytheria, 2020. “Error Detection in English and Greek texts written by foreign learners“, MSc Thesis, Digital Methods for the Humanities (pdf).

Korre Katerina, 2020. “Using Predictive Text for Grammatical Error Correction in Second Language Learning”. MSc Thesis, Digital Methods for the Humanities (pdf, slides).

Publications

Accepted papers

• Randl, K., Rocchietti, G., Henriksson, A., Abedjan, Z., Lindgren, T., Pavlopoulos, J. (2026). Quantifying Retriever-Generator Alignment in RAG with Local Explanations. Accepted at Findings of EMNLP 2026. Acceptance announcement; preprint, titled RAG-E: Quantifying Retriever-Generator Alignment and Failure Modes.

Publications in proceedings of peer-reviewed venues

• Pavlopoulos, J., Bakagianni, J. (2026). Edge-Capable Open-Weight LLMs in Modern Greek NLP: A Reproducible Benchmark. 14th EETN Conference on Artificial Intelligence (SETN 2026), Chania, Greece. Conference program.

• Lislevand, V., Stamatis, K., Bakagianni, J., Kougia, V., Dalakleidi, K. V., Pavlopoulos, J. (2026). Can Small Models Have Big Impact? Efficient Greek Clinical Text De-identification via Synthetic Augmentation. 14th EETN Conference on Artificial Intelligence (SETN 2026), Chania, Greece. Conference program.

• Semoglou, A., Likas, A., Pavlopoulos, J. (2026). Composite Silhouette. In Machine Learning and Knowledge Discovery in Databases. Research Track (ECML PKDD 2026), Part I. Springer. DOI; preprint; code and publication details.

• Pavlopoulos, J., Barbakos, S., Ferretti, L., Voulgarakis, D., Paparrigopoulou, A., Konstantinidou, M., De Gregorio, G., Marthot-Santaniello, I., Platanou, P., Essler, H. (2026). Learning Diachronic Representations of Ancient Greek Letterforms. In Document Analysis and Recognition – ICDAR 2026, Part III, pp. 158–174. Springer. DOI; preprint.

• Kaliosis, P., Pavlopoulos, J. (2025). Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition. In Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 18667–18684. Paper.

• Korre, K., Tsirmpas, D., Gkoumas, N., Cabalé, E., Myrtzani, D., Evgeniou, T., Androutsopoulos, I., Pavlopoulos, J. (2025). Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey. In Proceedings of EMNLP 2025, pp. 24443–24462. Paper.

• Randl, K., Pavlopoulos, J., Henriksson, A., Lindgren, T., Bakagianni, J. (2025). SemEval-2025 Task 9: The Food Hazard Detection Challenge. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pp. 2523–2534. Paper.

• Eleftheriou, K., Louridas, P., Pavlopoulos, J. (2025). KostasThesis2025 at SemEval-2025 Task 10 Subtask 2: A Continual Learning Approach to Propaganda Analysis in Online News. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pp. 899–908. Paper.

• Loukas, L., Smyrnioudis, N., Dikonomaki, C., Barbakos, S., Toumazatos, A., Koutsikakis, J., Kyriakakis, M., Georgiou, M., Vassos, S., Pavlopoulos, J., Androutsopoulos, I. (2025). GR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek. In Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations, pp. 174–182. Paper.

• Boumpi, M., Dalakleidi, K. V., Pavlopoulos, J. (2025) From Pen to Prediction: Handwriting-Based Alzheimer’s Detection. In IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE), pages 671-675, Athens, Greece, 2025, https://doi.org/10.1109/BIBE66822.2025.00116 [accepted version, slides, demo]

• Bakagianni, J. et al. (2025) DiaShift: An Explainable System for Temporal Diagnostic Shift Detection in Clinical Notes. In IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE), Athens, Greece, 2025, pp. 341-345, https://doi.org/10.1109/BIBE66822.2025.00063

• Bakagianni, J. et al. (2025) FoodSafeSum: Enabling Natural Language Processing Applications for Food Safety Document Summarization and Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 16786-16804, Suzhou, China. Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-emnlp.911

• Dimakis, A., Pavlopoulos, J., Anastasopoulos, A. (2025). Dialect Normalization using Large Language Models and Morphological Rules. In Findings of the Association for Computational Linguistics: ACL 2025, pages 23696–23714, Vienna, Austria. Association for Computational Linguistics.

• Randl, K., Pavlopoulos, J., Henriksson, A., Lindgren, T. (2024). CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification. In Findings of the Association for Computational Linguistics: ACL 2024, pp. 7695–7715. Paper.

• Kaliosis, P., Pavlopoulos, J., Charalampakos, F., Moschovis, G., Androutsopoulos, I. (2024). A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning. In Findings of the Association for Computational Linguistics: ACL 2024, pp. 7450–7466. Paper.

• Toumazatos, A., Pavlopoulos, J., Androutsopoulos, I., Vassos, S. (2024). Still All Greeklish to Me: Greeklish to Greek Transliteration. In Proceedings of LREC-COLING 2024, pp. 15309–15319. Paper.

• Pavlopoulos, J., Sandell, R., Konstantinidou, M., Bozzone, C. (2024). HoLM: Analyzing the Linguistic Unexpectedness in Homeric Poetry. In Proceedings of LREC-COLING 2024, pp. 8166–8172. Paper.

• Pavlopoulos, J., Vardakas, G., Likas, A. (2024). Revisiting Silhouette Aggregation. In the 27th International Conference on Discovery Science 2024. Pisa, Italy. (BEST PAPER, a preprint is present: arXiv:2401.05831).

• Pavlopoulos, J., Louridas, P., & Filos, P. (2024). Towards a Greek Proverb Atlas: A Computational Spatial Exploration and Attribution of Greek Proverbs. In the Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, USA. https://aclanthology.org/2024.emnlp-main.661/

• Randl, K., Pavlopoulos, J., Henriksson, A., & Lindgren, T. (2024). Evaluating the Reliability of Self-Explanations in Large Language Models. In International Conference on Discovery Science. Cham: Springer Nature Switzerland. Related preprint: arXiv preprint arXiv:2407.14487. https://link.springer.com/chapter/10.1007/978-3-031-78977-9_3

• De Gregorio, G., Ferretti, L., Pena, R. C., Marthot-Santaniello, I., Konstantinidou, M., & Pavlopoulos, J. (2024, August). A New Framework for Error Analysis in Computational Paleographic Dating of Greek Papyri. In International Conference on Document Analysis and Recognition (pp. 102-118). Cham: Springer Nature Switzerland.

• Pavlopoulos, J., Kougia, V., Arias, E.G., Platanou, P., Shabalin, S., Liagkou, K., Papadatos, E., Essler, H., Camps, J.B. and Fischer, F., 2024. Challenging Error Correction in Recognised Byzantine Greek. In Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024) (pp. 1-12). (BEST PAPER)

• Konstantinidou, M., Pavlopoulos, J., & Barker, E. (2024, August). Exploring intertextuality across the Homeric poems through language models. In Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024) (pp. 260-268).

• Pavlopoulos J. and Likas A., 2024. Polarized Opinion Detection Improves the Detection of Toxic Language. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Malta, pp. 1946–1958. https://aclanthology.org/2024.eacl-long.117 (slides, poster, video)

• Pavlopoulos J., Kougia V., Platanou P. and Essler H., 2023. Detecting Erroneous Handwritten Byzantine Text Recognition. In Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore (slides; accepted manuscript)

• Liagkou K., Pavlopoulos J., Machotka E. 2023. Leveraging the Spatiotemporal Analysis of Meisho-e Landscapes. In Proceedings of the 26th International Conference of Discovery Science. Porto, Portugal (accepted manuscript)

• Pavlopoulos J., Konstantinidou M., Vardakas G., Marthot-Santaniello I., Perdiki E., Koutsianos D., Likas A., Essler H., 2023. Explaining the Chronological Attribution of Greek Papyri Images. In Proceedings of the 26th International Conference of Discovery Science. Porto, Portugal (accepted manuscript).

• Pavlopoulos, J., Konstantinidou, M., Marthot-Santaniello, I., Essler, H., & Paparigopoulou, A., 2023. Dating Greek Papyri with Text Regression. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 10001-10013. https://aclanthology.org/2023.acl-long.556 (video).

• Dritsa, K., Thoma, A., Pavlopoulos, I. and Louridas, P., 2022. A Greek Parliament Proceedings Dataset for Computational Linguistics and Political Analysis. Advances in Neural Information Processing Systems, 35, pp.28874-28888.

• Zonios, C., Pavlopoulos, J., Likas, A., 2022. Transformer-Based Music Language Modelling and Transcription. In Proceedings of the 12th Hellenic Conference on Artificial Intelligence (SETN ‘22). https://doi.org/10.1145/3549737.3549754.

• Platanou, V., Pavlopoulos, J., Papaioannou, G., 2022. Handwritten Paleographic Greek Text Recognition: a Century-Based Approach. In Proceedings of the Language Resources and Evaluation Conference (LREC). Marseille, France and online, June 2022.

• Pavlopoulos, J., Xenos, A., Picca, A., 2022. Annotating the Sentiment of Homeric Text. In Proceedings of the Language Resources and Evaluation Conference (LREC). Marseille, France and online, June 2022.

• Liagkou, K., Pavlopoulos, J., Machotka, E., 2022. A Study of Distant Viewing of ukiyo-e prints. In Proceedings of the Language Resources and Evaluation Conference (LREC). Marseille, France and online, June 2022.

• Pavlopoulos, J., Laugier, L., Xenos, A., Sorensen, J., Androutsopoulos, I., 2022. From the Detection of Toxic Spans in Online Discussions to the Analysis of Toxic-to-Civil Transfer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3721–3734, Dublin, Ireland. Paper.

• Chatzipanagiotou, M., Machotka, E., Pavlopoulos, J., 2021. Automated recognition of geographical named entities in titles of Ukiyo-e prints. In Digital Humanities Workshop (DHW 2021). Association for Computing Machinery, New York, NY, USA, 70–77. DOI:https://doi.org/10.1145/3526242.3526254

• Fasoi, M., Pavlopoulos, J., Konstantinidou, M., 2021. Computational Authorship Analysis of Homeric Language. In Digital Humanities Workshop (DHW 2021). Association for Computing Machinery, New York, NY, USA, 78–88. DOI:https://doi.org/10.1145/3526242.3526256

• Ljungman, J., Lislevand, V., Pavlopoulos, J., Farazouli, A., Lee, Z., Papapetrou, P., Fors, U., 2021. Automated Grading of Exam Responses: An Extensive Classification Benchmark. In International Conference on Discovery Science. Springer, Cham. pp. 3-18.

• Miliou, I., Pavlopoulos, J., Papapetrou, P., 2021. Sentiment Nowcasting During the COVID-19 Pandemic. In International Conference on Discovery Science, pp. 218-228 (link).

• Kougia, V. and Pavlopoulos, J., 2021. Multimodal or Text? Retrieval or BERT? Benchmarking Classifiers for the Shared Task on Hateful Memes. In the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 220-225

• Xenos, A. and Pavlopoulos, J. and Androutsopoulos, I., 2021. Context sensitivity estimation in toxicity detection. In the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 140-145.

• Pavlopoulos, J., Sorensen, J., Laugier, L. and Androutsopoulos, I., 2021, August. SemEval-2021 task 5: Toxic spans detection. In Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021) (pp. 59-69).

• Pavlopoulos, J. and Papapetrou, P., 2021. Customized Neural Predictive Medical Text: A Use-Case on Caregivers. In Artificial Intelligence in Medicine: 19th International Conference on Artificial Intelligence in Medicine, AIME 2021, Virtual Event, June 15–18, 2021, Proceedings (pp. 438-443). Springer International Publishing.

• Laugier, L., Pavlopoulos, J., Sorensen, J. and Dixon, L., 2021. Civil Rephrases Of Toxic Texts With Self-Supervised Transformers. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 1442–1461. Paper.

• Korre, K. and Chatzipanagiotou, M. and Pavlopoulos, J., 2021. ELERRANT: Automatic Grammatical Error Type Classification for Greek. In RANLP, pp. 708-717.

• Korre, K. and Pavlopoulos, J., 2020. ERRANT: Assessing and Improving Grammatical Error TypeClassification. In LaTeCH-CLfL.

• Pavlopoulos, J. and Papapetrou P., 2020. Clinical Predictive Keyboard using Statistical and Neural Language Modeling. In CBMS.

• Pavlopoulos, J. and Sorensen, J. and Dixon, L. and Thain, N. and Androutsopoulos, I., 2020. Toxicity Detection: Does Context Really Matter? In ACL.

• Kougia V., Pavlopoulos, J. and Androutsopoulos, I., 2020. Medical Image Tagging with Neural Retrieval and Deep Learning. In LNCS.

• Kougia V., Pavlopoulos, J. and Androutsopoulos, I., 2019. AUEB NLP Group at ImageCLEFmed Caption 2019. In the International Conference and Labs of the Evaluation Forum for European Languages.

• Kougia, V., Pavlopoulos, J. and Androutsopoulos, I., 2019. A Survey of Biomedical Image Captioning. In Proceedings of the Shortcomings in Vision and Language NAACL Workshop, Minneapolis, MN, USA.

• Pavlopoulos, J., Malakasiotis, P., Bakagianni, J. and Androutsopoulos, I., 2017. Improved Abusive Comment Moderation with User Embeddings. In Proceedings of the Natural Language Processing meets Journalism Workshop in EMNLP, Copenhagen, Denmark, pp. 51—55.

• Pavlopoulos, J., Malakasiotis, P. and Androutsopoulos, I., 2017. Deep Learning for User Comment Moderation. In Proceedings of the 1st Abusive Language Workshop in ACL, Vancouver, BC, Canada, pp. 25—35.

• Pavlopoulos, J., Malakasiotis, P. and Androutsopoulos, I., 2017. Deeper Attention to abusive user comment moderation. In EMNLP, Copenhagen, Denmark, pp. 1125—1135.

• Giorgis, S., Rousas, A., Pavlopoulos, J., Malakasiotis, P. and Androutsopoulos, I., 2016. Aueb.twitter.sentiment at SemEval-2016 Task 4: A weighted ensemble of SVMs for Twitter sentiment analysis. In Proceedings of SemEval in NAACL:HLT, San Diego, California, USA, pp. 96—99.

• Xenos, D., Theodorakakos, P., Pavlopoulos, J., Malakasiotis, P. and Androutsopoulos, I., 2016. Aueb-absa at semeval-2016 task 5: Ensembles of classifiers and embeddings for aspect based sentiment analysis. In Proceedings of SemEval in NAACL:HLT, San Diego, California, USA, pp. 312—317.

• Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I. and Manandhar, S., 2014. Semeval-2014 task 4: Aspect based sentiment analysis. In Proceedings of SemEval in EACL, Dublin, Ireland, pp. 27—35.

• Pavlopoulos, J. and Androutsopoulos, I., 2014. Aspect term extraction for sentiment analysis: New datasets, new evaluation measures and an improved unsupervised method. In Proceedings of the 5th Workshop on Language Analysis for Social Media in EACL, Gothenburg, Sweden, pp. 44—52.

• Karampatsis, R. M., Pavlopoulos, J. and Malakasiotis, P., 2014. AUEB: Two stage sentiment analysis of social network messages. In Proceedings of SemEval in ACL, Dublin, Ireland, pp. 114—118.

• Pavlopoulos, J. and Androutsopoulos, I., 2014. Multi-granular aspect aggregation in aspect-based sentiment analysis. In EACL, Gothenburg, Sweden, pp.78–87.

• Alexopoulos, P., Pavlopoulos, J. and Mylonas, P., 2012. Learning vague knowledge from socially generated content in an enterprise framework. In IFIP Advances in Information and Communication Technology, Artificial Intelligence Applications and Innovations, Halkidiki, Greece, pp. 510–519.

• Alexopoulos, P., Pavlopoulos, J., Wallace, M. and Kafentzis, K., 2011. Exploiting ontological relations for automatic semantic tag recommendation. In Proceedings of the 7th International Conference on Semantic Systems, Graz, Austria, pp. 105—110.

• Voudigari, E., Pavlopoulos, J. and Vazirgiannis, M., 2011. A Framework for Web Page Rank Prediction. In Proceedings of Engineering Applications of Neural Networks / Artificial Intelligence Applications and Innovations, Corfu, Greece, pp. 240—249.

• Vrettaros, J., Pavlopoulos, J., Vouros, G. and Drigas, S., 2008. The development of a self-assessment system for the learners answers with the use of GPNN. In Proceedings of the World Summit on Knowledge Society (WSKS), Athens, Greece, pp.332—340.

Book chapters

• Konstantinidou, M., Pavlopoulos, J. (2026). Approaching Homer with NLP. In E. Barker, O. Bobou, R. Raja (eds.), The Oxford Handbook of Digital Classical Studies, pp. 675–689. Oxford University Press. DOI.

Journal articles

• Semoglou, A., Pavlopoulos, J. (2026). CAKE: Confidence in Assignments via K-partition Ensembles. Machine Learning with Applications, 24, 100915. DOI; preprint.

• Georgiadis, T., Pavlopoulos, J., Mamoulis, N. (2026). SpaRAGraph: Spatial Reasoning using Retrieval-Augmented Generation. ACM Transactions on Spatial Algorithms and Systems. DOI.

• Randl, K., Pavlopoulos, J. et al. Mind the gap: from plausible to valid self-explanations in large language models. Mach Learn 114, 220 (2025). https://doi.org/10.1007/s10994-025-06838-6

• Assael, Y., Sommerschield, T., Cooley, A., Shillingford, B., Pavlopoulos, J. et al. 2025. Contextualizing ancient texts with generative neural networks. Nature. https://doi.org/10.1038/s41586-025-09292-5

• Bakagianni, J., Pouli, K., Gavriilidou, M., Pavlopoulos, J., 2025. A systematic survey of natural language processing for the Greek language. Patterns 6, no. 11. https://doi.org/10.1016/j.patter.2025.101313

• Barmpounis E.-K., Pavlopoulos, J., Louridas, P., Dritsa, K., 2024. Recognition and Analysis of the Proceedings of the Greek Parliament after WWII. DHQ 18(1). https://www.digitalhumanities.org/dhq/vol/18/1/000736/000736.html (data at: https://zenodo.org/records/8302990; Transkribus model under the name “Greek Parliamentary Proceedings 1946”)

• Pavlopoulos J., Romell A., Curman J., Steinert O., Lindgren T., Borg M., and Randl K., 2023. Automotive Fault Nowcasting with Machine Learning and Natural Language Processing. Machine Learning. https://doi.org/10.1007/s10994-023-06398-7

• Sommerschield, T., Assael, Y., Pavlopoulos, J., Stefanak, V., Senior, A., Dyer, C., Bodel, J., Prag, J., Androutsopoulos, I. and de Freitas, N., 2023. Machine Learning for Ancient Languages: A Survey. Computational Linguistics, pp.1-44. https://doi.org/10.1162/coli_a_00481

• Boulieris, P., Pavlopoulos, J., Xenos, A., & Vassalos, V., 2023. Fraud detection with natural language processing. Machine Learning, 1-22. https://doi.org/10.1007/s10994-023-06354-5

• Pavlopoulos, J., Likas, A., 2022. Distance from Unimodality for the Assessment of Opinion Polarization. Cognitive Computation. https://doi.org/10.1007/s12559-022-10088-2

• Pavlopoulos, J., Konstantinidou, M., 2022. Computational authorship analysis of the homeric poems. International Journal of Digital Humanities, 1-20.

• Pavlopoulos, J., Kougia, V., Androutsopoulos, I., Papamichail, D., 2022. Diagnostic Captioning: a Survey. Knowledge and Information Systems, 1-32. https://doi.org/10.1007/s10115-022-01684-7.

• Xenos, A., Pavlopoulos, J., Androutsopoulos, I., Dixon, L., Sorensen, J., Laugier, L., 2022. Toxicity Detection can be Sensitive to the Conversational Context. First Monday, 27(5), 2022. https://doi.org/10.5210/fm.v27i5.12285.

• Assael, Y., Sommerschield, T., Shillingford, B., Bordbar, M., Pavlopoulos, J., Chatzipanagiotou, M., Androutsopoulos, I., Prag, J., de Freitas., N., 2022. Restoring and attributing ancient texts with deep neural networks. In Nature.

• Olczak J., Pavlopoulos J., Prijs J., Ijpma F. F. A., Doornberg J. N., Lundstrom C., Hedlund J., and Gordon M., 2021. Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal. Acta Orthopaedica.

• Kougia, V., Pavlopoulos, J., Papapetrou, P., Gordon, M. (2021). RTEx: A novel framework for ranking, tagging, and explanatory diagnostic captioning of radiography exams. Journal of the American Medical Informatics Association, 28(8), pp. 1651–1659.

• Tsatsaronis G., Balikas G., Malakasiotis P., Partalas I., Zschunke, M., Alvers, M., Weissenborn, D., Krithara, A., Petridis, S., Polychronopoulos, D., Almirantis, Y., Pavlopoulos, J., Baskiotis, N., Gallinari, P., Artieres, T., Ngomo, A.-C., Heino, N., Gaussier, E.; Barrio-Alvers, L., Schroeder, M., Androutsopoulos, I. and Paliouras, G., 2015. An overview of the bioasq large-scale biomedical semantic indexing and question answering competition. BMC Bioinformatics 16(1).

• Alexopoulos P., Pavlopoulos J. and Mylonas P., “A Semantic Framework for Harvesting Vague Enterprise Knowledge from Microposts”. International Journal on Artificial Intelligence Tools 23(02), 2014.

• Vrettaros J., Pavlopoulos J., Drigas A. S. and Hrissagis K., “GPNN techniques in learning assessment systems”. In International Journal of Technology Enhanced Learning. Inderscience Publishers, pp. 415—429, 3(4), 2011.

Preprints

• Tsirmpas, D., Korre, K., Pavlopoulos, J. (2026). To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussions. arXiv:2607.28643.

• Tzachristas, I., Pavlopoulos, J. (2026). Aristotelian Virtue Profiling of LLMs through Ethical Dilemmas. arXiv:2606.28683.

• Tsirmpas, D., Pavlopoulos, J. (2026). Quantifying and Attributing Polarization to Annotator Groups. arXiv:2602.06055.

• Korre, K., Pavlopoulos, J. (2025). Proverbs or Pythian Oracles? Sentiments and Emotions in Greek Sayings. arXiv:2510.13341.

• Bakagianni, J., Pavlopoulos, J., Likas, A. (2025). TopClustRAG at SIGIR 2025 LiveRAG Challenge. arXiv:2506.15246.

• Pavlopoulos, J., Bakagianni, J., Pouli, K., Gavriilidou, M. (2025). Open or Closed LLM for Lesser-Resourced Languages? Lessons from Greek. arXiv:2501.12826.

Doctoral and master’s theses

• Pavlopoulos, J., 2014. Aspect Based Sentiment Analysis. PhD Thesis, Athens University of Economics and Business, Department of Informatics, Greece, Supervisor: Professor Ion Androutsopoulos.

• Pavlopoulos, J., 2009. Implementation and Comparison of models addressing Automatic Text Illustration, MSc Dissertation, University of Edinburgh, School of Informatics, U.K., Supervisor: Professor Mirella Lapata.