Dimitra Gkatzia
Dimitra Gkatzia

Dr Dimitra Gkatzia

Associate Professor

Biography

Dimitra Gkatzia is an Associate Professor at the School of Computing at Edinburgh Napier University. She received her PhD in Computer Science from Heriot-Watt University (Edinburgh, UK) in 2015. Her thesis focused on Natural Language Generation (i.e. automatic production of human language) developing machine learning methods for automatic summarisation of time-series data (health data from sensors, database entries that change over time, other seasonal data) into natural language summaries with the goal to enhance comprehension and promote decision making. 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. In 2016, Dimitra joined Edinburgh Napier University as a lecturer, and was later promoted to Associate Professor. She is also a Fellow of the Higher Education Academy, holds an MSc in Artificial Intelligence (Distinction - top student of the degree) from Heriot-Watt and a BSc (Hons) in Digital Systems from the University of Piraeus (Greece).

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.

She is interested in exploring data-driven Natural Language Generation (NLG) for low-resource domains/languages, i.e. domains where parallel data is hard to acquire and annotate as well as domains where tools that are useful for NLG are not available. In this sense, low-resource NLG describes all areas that require careful collection and annotation of data, might require expert input (as in health domain) which might be hard to acquire or data that in general is not publicly available. In addition to inaccessibility of data, generating text with linguistic variability can be a challenge when not enough example texts are available.

This work is also complemented by her current work on Human-Robot Interaction, where she investigates the interplay between various modalities (vision, speech, knowledge-bases) in real-world settings for human-robot teaming scenarios. Her work in this area focuses on enhancing NLG with commonsense capabilities similar to the ones present in human-human communication. This has also motivated work on privacy-preserving methods for Natural Language Processing as well as on ethical and responsible innovation more widely.

INTERNATIONAL DISTINCTIONS

- Keynote speaker at the International Natural Language Generation Conference (INLG 2022)
- Panel Member at Scottish AI Summit (2022)
- Best paper award at International Natural Language Generation Conference (INLG 2021).
- Nomination for Best LBR Paper Award in Human-Robot Interaction (HRI) 2021.
- Women in Robotics Spotlight at Robohub.

RESEARCH LEADERSHIP

Since 2021, Dimitra is the co-lead of the SICSA (Scottish Informatics and Computer Science Alliance) AI Theme, which aims to strengthen research collaborations between SICSA members working in AI and related disciplines, leading to long-lasting interdisciplinary research partnerships; stimulate improved collaboration between the various research sub-groups to identify new and emerging research areas; share  knowledge, expertise and tools to enhance AI research. Between 2016-2020, Dimitra served as an elected member of the Steering Board of the Special Interest Group in Natural Language Generation (SIGGEN). At Edinburgh Napier, Dimitra is currently leading the Natural Language Processing Group.

Dimitra has also contributed to the organisation of major scientific events: she is a co-founder of the NLG4HRI workshop series (2018, 2020), has acted as chair for various International research meetings including 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.

SELECTED CURRENT PROJECTS

* Natural Language Generation for low-resource domains (EPSRC, 2021 – 2024), PI
* CiViL: Commonsense and Visually enhanced natural Language generation (EPSRC, 2020-2023), PI
* Enhancing Labour Market Intelligence using Machine Learning (ESRC & SDS, 2021-2024): co-Investigator, co-PI
* Natural language interfaces to support career decision-making of young people (ESRC & SDS, 2020 – 2023): co-PI
* Intelligent Agents (Innovate UK, 2019 – 2022): co-I
* Multi3Generation (COST Action, 2019-2023): WG3 Leader until 2021, proposer

PAST PROJECTS (involved as a researcher):

* GUI: Generation for Uncertain Information, (EPSRC, 2014-2015)
* ATME: Summarising sensor data for medical emergencies (Royal Society, 2013-2014)

News

Events

Esteem

Advisory panels and expert committees or witness

  • Research Theme Leader: co-lead of the Scottish Informatics and Computer Science Alliance (SICSA) Research Theme on Artificial Intelligence
  • Management committee member: Mulit3Generation COST Action
  • Advisory Board: Steering Board Member of the ACL Special Interest Group in Natural Language Generation

 

Conference Organising Activity

  • Mentor (PhD mentoring session): Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), virtual, 2021
  • Workshop Organiser: 1st Workshop on Evaluating NLG Evaluation
  • Programme Committee Chair: Demo Chair for the European Chapter of the Association for Computational Linguistics (EACL 2021), Kyiv, Ukraine (online), 2021
  • Ethics Committee Member: Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), virtual, 2021
  • Invited to join the Programme Committee of the 28th International Conference on Computational Linguistics (COLING), Barcelona, Spain, 2020
  • Workshop organiser: Co-organiser of the 2nd Workshop on Natural Language Generation for Human-Robot Interaction, Dublin, Ireland (online), 2020
  • Conference Programme (Area) Chair: the 12th International Conference on Natural Language Generation (INLG) 2019, Tokyo, Japan
  • Workshop organiser: Co-organiser of the 1st Workshop on Natural Language Generation for Human-Robot Interaction, Tilburg, Netherlands, 2018
  • Dimitra Gkatzia invited on to the Programme Committee of the annual meeting of the Association for Computational Linguistics (ACL), Melbourne, 2018
  • Conference Programme (Area) Chair: the North American Chapter on Computational Linguistics (NAACL), New Orleans, USA, 2018
  • Tutorial and Invited Talks Chair: the 10th International Conference on Natural Language Generation (INLG), Santiago de Compostela, Spain, 2017
  • Conference Organiser: the 9th International Natural Language Generation conference (INLG), Edinburgh, UK, 2016
  • Conference Chair: the 9th International Natural Language Generation conference (INLG), Edinburgh, UK, 2016
  • Workshop Organiser: International Workshop on Data-to-text Generation, Edinburgh, UK, 2015
  • Registration chair and Student Volunteer coordinator: 23rd IEEE International Symposium on Robot and Human Interactive Communication, Edinburgh, UK, 2014

 

Editorial Activity

  • Editorial Board Member: Natural Language Engineering
  • Editorial Board Member: Special Issue on Natural Language Generation for Spoken Dialogue Systems (NLG4SDS) at Dialogue & Discourse journal. 2018
  • Editorial Board Member: Journal of Advanced Robotics

 

Fellowships and Awards

  • Award for Outstanding Position Paper at the 14th International Conference on Natural Language Generation (INLG 2021)
  • Nomination for the Best LBR Award at the ACM/IEEE International Conference on Human-Robot Interaction, virtual, 2021
  • Outstanding Reviewer acknowledgement: the 58th Annual Meeting of the Association for Computational Linguistics (online), 2020
  • Outstanding Reviewer acknowledgement: the 58th Annual Meeting of the Association for Computational Linguistics (online), Melbourne, Australia, 2018
  • Fellow of the Higher Education Academy (Associate Fellow since 2012)

 

Grant Funding Panel Member

  • Funding Panel: ICT2023 Frontier AI Technologies (Academy of Finland)

 

Grant Reviewer

  • Grant reviewer: Engineering and Physical Sciences Research Council (EPSRC)
  • Grant Reviewer: Medical Research Council (MRC)

 

Invited Speaker

  • Invited talk at Verint
  • Invited Talk at Canon - Edinburgh
  • Invited Speaker at University of Aberdeen
  • SICSA workshop on Cognitive and Social Robotics
  • Invited talk at the University of Bielefeld
  • Seminar talk: Heriot-Watt University, Edinburgh, 2015
  • Invited talk: IROS '15 Workshop on Spatial Reasoning and Interaction for Real-World Robotics. Hamburg, Germany.
  • Seminar talk: Aalto University, Helsinki, 2014

 

Media Activity

  • Women in Robotics Spotlights mention

 

Public/Community Engagement

  • Invited to join Panel at Scottish AI Summit on Explainable AI
  • Mentor at Girl Geek Scotland initiative
  • Public Engagement: Explorathon at the Zoo

 

Research Degree External Examining

  • Assessment of a PhD thesis at the University of Alicante -Spain
  • External PhD Examiner at Loria Nancy (France)
  • 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 ACL 2021
  • Committee Member: the 1st SICSA PhD dissertation award
  • Programme Committee member for IntelLanG - Intelligent Information Processing and Natural Language Generation
  • Programme Committee Member for the Workshop on Widening NLP
  • Programme Committee member of the conference on Empirical Methods on Natural Language Processing (EMNLP)
  • 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 International Natural Language Generation conference, 2017
  • Programme Committee member of the annual meeting of the Association for Computational Linguistics (ACL), Berlin, 2016

 

Visiting Positions

  • Research visit at the University of Bielefeld (Germany, 2017)
  • Research Visit at Aalto University (Finland, 2014)

 

Date


44 results

Reproducing Human Evaluation of Meaning Preservation in Paraphrase Generation

Conference Proceeding
Watson, L. N., & Gkatzia, D. (in press)
Reproducing Human Evaluation of Meaning Preservation in Paraphrase Generation.
Reproducibility is a cornerstone of scientific research, ensuring the reliability and generalisability of findings. The ReproNLP Shared Task on Reproducibility of Evaluations ...

Unveiling NLG Human-Evaluation Reproducibility: Lessons Learned and Key Insights from Participating in the ReproNLP Challenge

Conference Proceeding
Watson, L., & Gkatzia, D. (2023)
Unveiling NLG Human-Evaluation Reproducibility: Lessons Learned and Key Insights from Participating in the ReproNLP Challenge. In Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems (69-74
Human evaluation is crucial for NLG systems as it provides a reliable assessment of the quality, effectiveness, and utility of generated language outputs. However, concerns ab...

Working with troubles and failures in conversation between humans and robots: workshop report

Journal Article
Förster, F., Romeo, M., Holthaus, P., Wood, L. J., Dondrup, C., Fischer, J. E., …Kapetanios, E. (2023)
Working with troubles and failures in conversation between humans and robots: workshop report. Frontiers in Robotics and AI, 10, Article 1202306. https://doi.org/10.3389/frobt.2023.1202306
This paper summarizes the structure and findings from the first Workshop on Troubles and Failures in Conversations between Humans and Robots. The workshop was organized to bri...

enunlg: a Python library for reproducible neural data-to-text experimentation

Conference Proceeding
Howcroft, D. M., & Gkatzia, D. (2023)
enunlg: a Python library for reproducible neural data-to-text experimentation. In Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations (4-5
Over the past decade, a variety of neural ar-chitectures for data-to-text generation (NLG) have been proposed. However, each system typically has its own approach to pre-and p...

Edge NLP for Efficient Machine Translation in Low Connectivity Areas

Conference Proceeding
Watt, T., Chrysoulas, C., & Gkatzia, D. (in press)
Edge NLP for Efficient Machine Translation in Low Connectivity Areas.
Machine translation (MT) usually requires connectivity and access to the cloud which is often limited in many parts of the world, including hard to reach rural areas. Edge nat...

Building a dual dataset of text-and image-grounded conversations and summarisation in Gàidhlig (Scottish Gaelic)

Conference Proceeding
Howcroft, D. M., Lamb, W., Groundwater, A., & Gkatzia, D. (2023)
Building a dual dataset of text-and image-grounded conversations and summarisation in Gàidhlig (Scottish Gaelic). In Proceedings of the 16th International Natural Language Generation Conference (443-448
Gàidhlig (Scottish Gaelic; gd) is spoken by about 57k people in Scotland, but remains an under-resourced language with respect to natural language processing in general and na...

LOWRECORP: the Low-Resource NLG Corpus Building Challenge

Conference Proceeding
Chandu, K. R., Howcroft, D., Gkatzia, D., Chung, Y., Hou, Y., Emezue, C., …Adewumi, T. (2023)
LOWRECORP: the Low-Resource NLG Corpus Building Challenge. In The 16th International Natural Language Generation Conference: Generation Challenges (1-9
Most languages in the world do not have sufficient data available to develop neural-network-based natural language generation (NLG) systems. To alleviate this resource scarcit...

Multi3Generation: Multi-task, Multilingual, Multi-Modal Language Generation

Presentation / Conference
Barreiro, A., de Souza, J. G., Gatt, A., Bhatt, M., Lloret, E., Erdem, A., …Alhasani, M. (2022, June)
Multi3Generation: Multi-task, Multilingual, Multi-Modal Language Generation. Poster presented at 23rd Annual Conference of the European Association for Machine Translation (EAMT 2022), Ghent, Belgium
This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an interdisciplinary network of research groups worki...

Opportunities and risks in the use of AI in career development practice

Journal Article
Wilson, M., Robertson, P., Cruickshank, P., & Gkatzia, D. (2022)
Opportunities and risks in the use of AI in career development practice. Journal of the National Institute for Career Education and Counselling, 48(1), 48-57. https://doi.org/10.20856/jnicec.4807
The Covid-19 pandemic required many aspects of life to move online. This accelerated a broader trend for increasing use of ICT and AI, with implications for both the world of ...

A Commonsense-enhanced Document-Grounded Conversational Agent: A Case Study on Task-based Dialogue

Conference Proceeding
Strathearn, C., & Gkatzia, D. (in press)
A Commonsense-enhanced Document-Grounded Conversational Agent: A Case Study on Task-based Dialogue. In ICNLSP Conference
This paper argues that future dialogue systems must be able to retrieve relevant information from multiple structured and unstructured data sources in order to generate natura...

Pre-Napier Funded Projects

  • SICSA funding for the organisation of the 1st International Workshop on Data-to-text (£700)

Current Post Grad projects