Ayal Klein

Ayal Klein

Hi, welcome to my homepage. My Portrait Picture

About

I am a Lecturer (Principal Investigator) in the Department of Computer Science, Ariel University, where I lead the NLP for Human Sciences Lab. My research explores the intersection of Artificial Intelligence and the Human Sciences, focusing on how Large Language Models (LLMs) can advance our understanding of complex human phenomena while enhancing scientific discovery itself.

Methodologically, I work on interpretable and causal NLP, with an emphasis on LLM interpretability, concept-based representations, and model-based reasoning that bridges data-driven AI and theory-driven science.

Before joining Ariel University, I was a post-doctoral researcher at Queen Mary University of London and Bar-Ilan University, working with Prof. Maria Liakata and Prof. Dana Atzil-Slonim on applying advanced NLP to psychotherapy research—aiming to uncover the mental processes and dynamics underlying effective therapeutic change.

I completed my B.Sc. (2015) in Psychology and Philosophy at Bar Ilan University, and my M.Sc. (2018) and Ph.D. (2024) in Computer Science, in the Natural Language Processing Lab at Bar Ilan University under the supervision of Prof. Ido Dagan. My doctoral research focused on semantic representations, particularly the QASem project).

My broader academic interests span psychology, cognitive and social sciences, linguistics, philosophy, mathematics, and computational methods — fields that together shape a vision of AI as a catalyst for integrative scientific understanding. I’m also enthusiastic about cross-disciplanry collaborations of AI and Data-Science specialists with social sciences and humanities, aiming at revolutionzing the way we investigate, measure and confirm/disprove scientific research questions in the ``softer’’ sciences.

The QASem project

In my Ph.D, we have devised a natural way to break down the information conveyed by langauge, using question-answer pairs. Our semantic framework, termed QASem (QA-based Semantics), consists of several annotation ‘layers’ covering different types of textual information or semantic relations. Our tool takes in a sentences and outputs a set of QAs that correspond to the basic information units in the sentence. You can take a look at the QASem demo or install its latest version it in your python environment through pip install qasem_parser. See our repo for further details (or Paul’s repo for the latest, more performant version).

Publications

Tseytlin, Maria, Paul Roit, Omri Abend, Ido Dagan, and Ayal Klein. “QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs.” Proceedings of the International Joint Conference on Natural Language Processing and the Asian Conference on Natural Language Processing (IJCNLP/AACL 2025) (forthcoming). 2025.

Klein, Ayal, Jiayu Song, Jenny Chim, Liran Keren, Andreas Triantafyllopoulos, Björn W. Schuller, Maria Liakata, and Dana Atzil-Slonim. “Clinical Summaries of Social Media Timelines for Mental Health Monitoring: Human vs. Large Language Model Comparative Evaluation.” JMIR Formative Research (forthcoming). doi:10.2196/71230. 2025.

Tseriotou, Talia, Jenny Chim, Ayal Klein, Aya Shamir, Guy Dvir, Iqra Ali, Cian Kennedy, Guneet Singh Kohli, Anthony Hills, Ayah Zirikly, Dana Atzil-Slonim, and Maria Liakata. “Overview of the CLPsych 2025 Shared Task: Capturing Mental Health Dynamics from Social Media Timelines.” In Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025), pages 193–217, Albuquerque, New Mexico. Association for Computational Linguistics. 2025.

Zhang, Shiyue, David Wan, Arie Cattan, Ayal Klein, Ido Dagan, and Mohit Bansal. “QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization.”. In Proceedings of the Conference on Language Modeling (COLM 2025). Association for Computational Linguistics. 2025.

Triantafyllopoulos, Andreas, Yannik Terhorst, Iosif Tsangko, Florian B. Pokorny, Katrin D. Bartl-Pokorny, Lennart Seizer, Ayal Klein, Jenny Chim, Dana Atzil-Slonim, Maria Liakata, Markus Bühner, Johanna Löchner, and Björn Schuller. “Large language models for mental health.” arXiv preprint arXiv:2411.11880. 2024.

Roit, Paul, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, and Ido Dagan. “Explicating the Implicit: Argument Detection Beyond Sentence Boundaries.” In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 16394–16409, Bangkok, Thailand. Association for Computational Linguistics. 2024.

Pesahov, Leon, Ayal Klein, and Ido Dagan. “QA-Adj: Adding Adjectives to QA-based Semantics.” In Proceedings of the Fourth International Workshop on Designing Meaning Representations, pp. 74–88, Nancy, France. Association for Computational Linguistics. 2023.

Klein, Ayal, Eran Hirsch, Ron Eliav, Valentina Pyatkin, Avi Caciularu, and Ido Dagan. “QASem Parsing: Text-to-text Modeling of QA-based Semantics.” In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7742–7756, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. 2022.

Klein, Ayal, Oren Pereg, Daniel Korat, Vasudev Lal, Moshe Wasserblat, and Ido Dagan. “Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction.” In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pp. 104-112. 2022.

Weiss, Daniela Brook, Paul Roit, Ayal Klein, Ori Ernst, and Ido Dagan. “QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions.” In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 9879-9894. 2021.

Klein, Ayal, Jonathan Mamou, Valentina Pyatkin, Daniela Stepanov, Hangfeng He, Dan Roth, Luke Zettlemoyer, and Ido Dagan. “QANom: Question-answer driven SRL for nominalizations.” In Proceedings of the 28th International Conference on Computational Linguistics, pp. 3069-3083. 2020.

Pyatkin, Valentina, Ayal Klein, Reut Tsarfaty, and Ido Dagan. “QADiscourse-Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines.” In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2804-2819. 2020.

Roit, Paul, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, and Ido Dagan. “Controlled Crowdsourcing for High-Quality QA-SRL Annotation.” In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7008-7013. 2020.

Teaching Experience

Contact

Feel free to contact me.

Email: ayal dot s dot klein at gmail dot com

I’m also at LinkedIn.