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).
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.
- 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.
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)