Dimitra Gkatzia

Dimitra Gkatzia

Dr Dimitra Gkatzia

Lecturer

Biography

Dimitra Gkatzia is a lecturer at the School of Computing at Edinburgh Napier University. She holds a BSc (Hons) from the University of Piraeus (Greece), an MSc on Artificial Intelligence (Distinction) from Heriot-Watt and a PhD in Computer Science from Heriot-Watt University (Edinburgh, UK). After her PhD, she was appointed postdoctoral researcher at Heriot-Watt's Interaction Lab investigating Natural Language Generation methods for information presentation of uncertain data, where she developed the Extended Weather Game for task-based evaluations for NLG (Gkatzia et al., 2015; Gkatzia et al., 2017). In 2016, Dimitra joined Edinburgh Napier University where she currently supervises 3 research students in the area of NLP, and has assumed the role of Programme Leader for BEng (Hons) Computing and Module Leader for Data Wrangling.

RESEARCH INTERESTS

Dimitra is interested in making computers and robots interact in a human-like way using natural language, while at the same time respecting the privacy of the users as well as protecting the environment (through Green AI). Specifically, she is interested in developing data-driven Natural Language Understanding and Generation techniques that utilise privacy-preserving methods by respecting users' sensitive information and instead employing transfer learning approaches. In addition, she is interested in making dialogue systems (such as Alexa, Siri) converse naturally, by enhancing their responses with commonsense and world knowledge. She envisions a future where humans and robots co-exist and collaborate in domestic, public and work settings.

CURRENT & UPCOMING PROJECTS

* Natural Language Generation for low-resource domains (EPSRC, 2020 – 2023: Principal Investigator
* CiViL: Commonsense and Visually enhanced natural Language generation (EPSRC, 2020-2023): Principal Investigator
* Natural language interfaces to support career decision-making of young people (ESRC & SDS, 2020 – 2023): co-Investigator
* Intelligent Agents (Innovate UK, 2019 – 2022): co-Investigator
* Multi3Generation (COST Action, 2019-2023): WG3 Leader

INTERNATIONAL DISTINCTIONS AND PROFESSIONAL SERVICE

- Since 2016, Dimitra is an elected member of the Steering Board of the Special Interest Group in Natural Language Generation (SIGGEN).

- Organisation of major scientific events: founder of the NLG4HRI workshop series (2018, 2020), EACL 2021 (Demo chair), NAACL 2018 (Area Chair), INLG 2019 (Area Chair), INLG 2016 (general chair & organiser), International Workshop on Data-to-text Generation 2015 (general chair, local chair, session chair), IEEE ROMAN 2014 (registration chair and coordination of student-volunteers, UKCI 2012 (social media coordinator).

- Programme Committee member (2015 - ): IntelLanG, EACL, Journal of Advanced Robotics, ACL, EMNLP, IJCAI, INLG, IEEE FUZZ, WiNLP, ACM ICMI.

Events

Esteem

Advisory panels and expert committees or witness

  • Steering Board Member of the ACL Special Interest Group in Natural Language Generation

 

Conference Activity

  • Demo Chair for the European Chapter of the Association for Computational Linguistics (EACL 2021)
  • Co-organiser of the 2nd Workshop on Natural Language Generation for Human-Robot Interaction
  • Programme Committee member for IntelLanG - Intelligent Information Processing and Natural Language Generation
  • Invited programme committee member of the 28th International Conference on Computational Linguistics
  • Area Chair for the 12th International Conference on Natural Language Generation (INLG) 2019, Tokyo, Japan
  • Area Chair for North American Chapter on Computational Linguistics (NAACL)
  • Dimitra Gkatzia invited on to the Programme Committee of the annual meeting of the Association for Computational Linguistics (ACL), Melbourne, 2018
  • ACL 2018: Top Reviewer Acknowledgement
  • Co-organiser of INLG 2018 Workshop on Natural Language Generation for Human-Robot Interaction
  • Dimitra was invited to be the Keynote Chair for INLG 2017
  • Organiser of the 9th International Natural Language Generation Conference (INLG) 2016
  • Chair of the International Natural Language Generation conference

 

Grant Reviewer

  • Dimitra was invited to review a grant proposal for the Medical Research Council (MRC)

 

Invited Speaker

  • Invited Speaker at University of Aberdeen
  • Invited Talk at Canon - Edinburgh
  • SICSA workshop on Cognitive and Social Robotics
  • Invited talk at the University of Bielefeld

 

Research Degree External Examining

  • External Examiner of a PhD thesis at the University of Aberdeen
  • Assessment of a PhD thesis at the University of Santiago De Compostella -Spain

 

Reviewing

  • Programme Committee Member for the Workshop on Widening NLP
  • Invited reviewer for the Special Issue on Natural Language Generation for Spoken Dialogue Systems (NLG4SDS) to be published as part of the Dialogue & Discourse journal
  • Programme Committee member of the conference on Empirical Methods on Natural Language Processing (EMNLP)
  • Programme Committee Member of the annual meeting of the International Natural Language Generation conference, 2017
  • Reviewer for the conference on Empirical Methods on Natural Language Processing (EMNLP)
  • Programme Committee member for the First Workshop on Women and Underrepresented Minorities in NLP
  • Programme Committee member of the annual meeting of the Association for Computational Linguistics (ACL), Berlin, 2016

 

Date


21 results

Commonsense-enhanced Natural Language Generation for Human-Robot Interaction

Conference Proceeding
Gkatzia, D. (in press)
Commonsense-enhanced Natural Language Generation for Human-Robot Interaction
Commonsense is vital for human communication, as it allows us to make inferences without explicitly mentioning the context. Equipping robots with commonsense knowledge would l...

Proceedings of the Workshop on NLG for Human–Robot Interaction

Conference Proceeding
(2018)
Proceedings of the Workshop on NLG for Human–Robot Interaction. In M. Ellen Foster, H. Buschmeier, & D. Gkatzia (Eds.),
Ellen Foster, M., H. Buschmeier, & D. Gkatzia (Eds.) (2018). Proceedings of the Workshop on NLG for Human–Robot Interaction.

Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction

Conference Proceeding
Belakova, J., & Gkatzia, D. (2018)
Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction. In Proceedings of the Workshop on NLG for Human–Robot Interaction. , (8-11
One of the most natural ways for human robot communication is through spoken language. Training human-robot interaction systems require access to large datasets w...

Inflection Generation for Spanish Verbs using Supervised Learning

Conference Proceeding
Barros, C., Gkatzia, D., & Lloret, E. (2017)
Inflection Generation for Spanish Verbs using Supervised Learning. In Proceedings of the First Workshop on Subword and Character Level Models in NLP. , (136-141). https://doi.org/10.18653/v1/W17-4120
We present a novel supervised approach to inflection generation for verbs in Spanish. Our system takes as input the verb’s lemma form and the desired features such as person, ...

Improving the Naturalness and Expressivity of Language Generation for Spanish

Conference Proceeding
Barros, C., Gkatzia, D., & Lloret, E. (2017)
Improving the Naturalness and Expressivity of Language Generation for Spanish. In Proceedings of the 10th International Conference on Natural Language Generation. , (41-50). https://doi.org/10.18653/v1/W17-3505
We present a flexible Natural Language Generation approach for Spanish, focused on the surface realisation stage, which integrates an inflection module in order to improve the...

Data-to-Text Generation Improves Decision-Making Under Uncertainty

Journal Article
Gkatzia, D., Lemon, O., & Rieser, V. (2017)
Data-to-Text Generation Improves Decision-Making Under Uncertainty. IEEE Computational Intelligence Magazine, 12(3), 10-17. https://doi.org/10.1109/MCI.2017.2708998
Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. This article presents a comparison of different information...

The REAL Corpus: a crowd-sourced corpus of human generated and evaluated spatial references to real-world urban scenes

Conference Proceeding
Bartie, P., Mackaness, W., Gkatzia, D., & Rieser, V. (2016)
The REAL Corpus: a crowd-sourced corpus of human generated and evaluated spatial references to real-world urban scenes. In 10th International Conference on Language Resources and Evaluation (LREC)
We present a newly crowd-sourced data set of natural language references to objects anchored in complex urban scenes (In short: The REAL Corpus – Referring Expressions Anchore...

How to Talk to Strangers: generating medical reports for first time users

Conference Proceeding
Gkatzia, D., Rieser, V., & Lemon, O. (2016)
How to Talk to Strangers: generating medical reports for first time users. In 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)https://doi.org/10.1109/FUZZ-IEEE.2016.7737739
We propose a novel approach for handling first-time users in the context of automatic report generation from timeseries data in the health domain. Handling first-time users is...

The REAL corpus

Dataset
Bartie, P., Mackaness, W., Gkatzia, D., & Rieser, V. (2016)
The REAL corpus. [Dataset]
Our interest is in people’s capacity to efficiently and effectively describe geographic objects in urban scenes. The broader ambition is to develop spatial models capable of e...

Natural Language Generation enhances human decision-making with uncertain information.

Conference Proceeding
Gkatzia, D., Lemon, O., & Rieser, V. (2016)
Natural Language Generation enhances human decision-making with uncertain information. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, (264-268). https://doi.org/10.18653/v1/P16-2043
Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. We present a comparison of different information presentati...

Current Post Grad projects