Chair in Computing Science
- About
-
- Email Address
- e.reiter@abdn.ac.uk
- Telephone Number
- +44 (0)1224 273443
- Office Address
Meston 243
Department of Computing Science
University of Aberdeen
King's College
Aberdeen
AB24 3UE- School/Department
- School of Natural and Computing Sciences
Biography
I have taught computing science and done research in Natural Language Generation at Aberdeen since 1995. I expect to retire in 2026 or 2027. For more information about me, please see my personal webpage ehudreiter.com
Internal Memberships
- Research ethics
- Research
-
Research Overview
Current Interests
- Natural language generation
- Data-to-text
- Medical applications
Current Research Students
- Nikolai Babakov (Santiago de Compostela)
- Jawwad Baig
- Giulia Pucci
- Adarsa Sivaprasad
- Mengxuan Sun
- Barkavi Sundararajan
- Iniakpokeikiye Thompson
Current Postdocs
- David Howcroft
Past Research Students
See my blog for a list of past research students I have supervised.
CLAN
The CLAN (Computational Linguistics at Aberdeen) resesarch group meets at 4PM every Wednesday. Every week we discuss a research paper, idea, proposal, etc. CLAN meetings are open to everyone, contact me for more information or to be put on the mailing list.
I sometimes tweet CLAN information on @EhudReiter. Feel free to subscribe, most of my tweets are relevant to NLG research. Similarly my blog (ehudreiter.com) is mostly about NLG research.
Current Research
My current research focuses on (A) evaluation of natural language generation and (B) using AI and NLG to support patients, especially in their homes.
Funding and Grants
- Philhumans (EU) (2019-2023) - Using AI to support personal health apps.
- NL4XAI (EU) (2019-2024) - Explaining AI reasoning in natural language
- ReproHum (EPSRC) (2021-2024) - Investigating Reproducibility of Human Evaluations in Natural Language Processing
- ASICA (Cancer Research UK) (2024-2026): Achieving Self-directed Integrated Cancer Aftercare (ASICA) in melanoma
- Al-ʿĀmīyah (Colloquial Arabic) and generative AI (Royal Society Edinburgh) (2024-2025)– a snapshot of its emerging text-to-text abilities
- Teaching
-
Teaching Responsibilities
- Publications
-
Page 1 of 4 Results 1 to 50 of 160
Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsCommon Flaws in Running Human Evaluation Experiments in NLP
Computational Linguistics, vol. 50, no. 2, pp. 795–805Contributions to Journals: ArticlesLinguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsSmartphone-based extendable telematic data collection app
Software Impacts, vol. 19, 100601Contributions to Journals: ArticlesEvaluation of Human-Understandability of Global Model Explanations Using Decision Tree
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-031-50396-2_3
- [OPEN ACCESS] http://aura.abdn.ac.uk/bitstream/2164/22828/1/Sivaprasad_etal_ECAI_Evaluation_of_Human_VOR.pdf
- [ONLINE] View publication in Scopus
- [ONLINE] https://ecai2023.eu/
- [ONLINE] https://xai3ecai2023.github.io/
Evaluation of Human-Understandability of Global Model Explanations using Decision Tree
Working Papers: Preprint Papers- [ONLINE] http://arxiv.org/abs/2309.09917v1
- [ONLINE] https://ecai2023.eu/
- [ONLINE] https://xai3ecai2023.github.io/
Enhancing Factualness and Controllability of Data-to-Text Generation via Data Views and Constraints
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsSmart Selection of Useful Insights from Wearables
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1109/ICASSPW59220.2023.10193140
- [ONLINE] View publication in Scopus
Non-Repeatable Experiments and Non-Reproducible Results: The Reproducibility Crisis in Human Evaluation in NLP
Findings of the Association for Computational Linguistics: ACL 2023. Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.). Association for Computational Linguistics, pp. 3676-3687, 12 pagesChapters in Books, Reports and Conference Proceedings: ChaptersInfluence of context on users’ views about explanations for decision-tree predictions
Computer Speech & Language, vol. 81, 101483Contributions to Journals: ArticlesEvaluating factual accuracy in complex data-to-text
Computer Speech & Language, vol. 80, 101482Contributions to Journals: ArticlesMissing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsAre Experts Needed?: On Human Evaluation of Counselling Reflection Generation
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsConsultation Checklists: Standardising the Human Evaluation of Medical Note Generation
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsError Analysis of ToTTo Table-to-Text Neural NLG Models
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsUser-Driven Research of Medical Note Generation Software
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsComparing informativeness of an NLG chatbot vs graphical app in diet-information domain
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsDrivingBeacon: Driving Behaviour Change Support System Considering Mobile Use and Geo-information
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsThe 2022 ReproGen Shared Task on Reproducibility of Evaluations in NLG: Overview and Results
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsThe Accuracy Evaluation Shared Task as a Retrospective Reproduction Study
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsBeyond calories: evaluating how tailored communication reduces emotional load in diet-coaching
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.18653/v1/2022.humeval-1.5
Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsAnno-Mi: A dataset of expert- annotated counselling dialogues
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsData Augmentation for Reliability and Fairness in Counselling Quality Classification
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] https://github.com/hslu-abiz/sdaih22/blob/gh-pages/preprints/Data%20Augmentation%20for%20Reliability%20and%20Fairness%20in%20Counselling%20Quality%20Classification%20(slides).pdf
- [OPEN ACCESS] http://aura.abdn.ac.uk/bitstream/2164/21803/1/Kumar_etal_Data_Augmentation_For_VoR.pdf
- [ONLINE] http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=159833
Explaining Decision-Tree Predictions by Addressing Potential Conflicts between Predictions and Plausible Expectations
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsGeneration Challenges: Results of the Accuracy Evaluation Shared Task
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsThe ReproGen Shared Task on Reproducibility of Human Evaluations in NLG: Overview and Results
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsUnaddressed challenges in persuasive dieting chatbots
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1145/3450614.3463602
A Systematic Review of Reproducibility Research in Natural Language Processing
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsA preliminary study on evaluating Consultation Notes with Post-Editing
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsTowards objectively evaluating the quality of generated medical summaries
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsInteractive Natural Language Technology for Explainable Artificial Intelligence
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] DOI: https://doi.org/10.1007/978-3-030-73959-1_5
- [ONLINE] View publication in Scopus
Neural Scoring of Logical Inferences from Data using Feedback
International Journal of Interactive Multimedia and Artificial Intelligence IJIMAI, vol. 6, no. 5, pp. 90-99Contributions to Journals: ArticlesExplaining Bayesian Networks in Natural Language: State of the Art andChallenges
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsA Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems
Contributions to Conferences: PapersArabic NLG Language Functions
Contributions to Conferences: PapersReproGen: Proposal for a Shared Task on Reproducibility of Human Evaluations in NLG
Contributions to Conferences: PapersShared Task on Evaluating Accuracy
Contributions to Conferences: PapersHow are you?: Introducing stress-based text tailoring
Contributions to Conferences: PapersIterative Neural Scoring of Validated Insight Candidates
Contributions to Conferences: PapersSportSett: Basketball - A robust and maintainable dataset for Natural Language Generation
Contributions to Conferences: PapersTowards a Generalised Framework for Behaviour Insight Mining
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsA NLG framework for user tailoring and profiling in healthcare
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings- [ONLINE] View publication in Scopus
A System for Automatic English Text Expansion
IEEE Access, vol. 7, no. 1, pp. 123320-123333Contributions to Journals: ArticlesNatural Language Generation Challenges for Explainable AI
Contributions to Conferences: PapersMaking Effective Use of Healthcare Data Using Data-to-Text Technology
Data Science for Healthcare: Methodologies and Applications. Consoli, S., Recupero, D. R., Petkovic, M. (eds.). Springer, pp. 119-145, 27 pagesChapters in Books, Reports and Conference Proceedings: Chapters (Peer-Reviewed)- [ONLINE] DOI: https://doi.org/10.1007/978-3-030-05249-2_4
- [ONLINE] View publication in Scopus
- [ONLINE] View publication in Mendeley
Fuzzy-Based Language Grounding of Geographical References: From Writers to Readers
International Journal of Computational Intelligence Systems, vol. 12, no. 2, pp. 970 - 983Contributions to Journals: ArticlesLying and computational linguistics
The Oxford Handbook of Lying. Meibauer, J. (ed.). Oxford University PressChapters in Books, Reports and Conference Proceedings: Chapters (Peer-Reviewed)Generating Summaries of Sets of Consumer Products: Learning from Experiments
Chapters in Books, Reports and Conference Proceedings: Conference ProceedingsMeteorologists and Students: A resource for language grounding of geographical descriptors
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings