Publications

Thesis

Dimitra GkatziaData-driven approaches to content selection for data-to-text generation. PhD Thesis, Heriot-Watt University. Edinburgh, UK, 2015. [PhDThesis]

2017

Dimitra Gkatzia , Oliver Lemon, and Verena Rieser. Data-to-Text Generation Improves Decision-Making Under Uncertainty. IEEE Computational Intelligence Magazine, Special Issue on Natural Language Generation with Computational Intelligence. 2017 (to appear). Impact Factor: 3.65. [pre-print]

Cristina Barros, Dimitra Gkatzia , and Elena Lloret. Improving the Naturalness and Expressivity of Language Generation for Spanish.  In Proceedings of the 10th International Conference on Natural Language Generation (INLG). 2017 (to appear). [pdf]

Cristina Barros, Dimitra Gkatzia , and Elena Lloret. Inflection Generation for Spanish Verbs using Supervised Learning. EMNLP Workshop on Subword and Character LEvel Models in NLP (SCLeM). 2017 (to appear). [pdf]

2016

Dimitra Gkatzia. Content Selection in Data-to-Text Systems: A SurveyarXiv:1610.08375 [cs.CL]. 2016. 

Dimitra Gkatzia, Oliver Lemon and Verena Rieser. Natural Language Generation enhances human decision-making with uncertain information. In Proceedings of the 54rth Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany, 2016 (2016 acceptance rate: 21%). [pdf] [ppt] [talk] [data]

Dimitra Gkatzia, Verena Rieser and Oliver Lemon. How to Talk to Stranger:  Generating Medical Reports for First-Time Users. In Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ) and the IEEE World Congress on Computational Intelligence (IEEE WCCI). Vancouver, Canada, 2016. [pdf][ppt] [data]

Phil Bartie, William Maccaness, Dimitra Gkatzia and Verena Rieser. The REAL Corpus: A Crowd-Sourced Corpus of Human Generated and Evaluated Spatial References to Real-World Urban Scenes. In Proceedings of the 10th Language Resources and Evaluation Conference (LREC). Portorož, Slovenia, 2016. [pdf ] [data ]

2015

Dimitra Gkatzia, Verena Rieser, Phil Bartie and William Mackaness. From the Virtual to the Real World: Referring to Objects in Spatial Real-World Scenes. In Proc. of EMNLP. Lisbon, Portugal, 2015 (2015 acceptance rate: 24%). [pdf] [GitHub] [data]

David McGookin, Dimitra Gkatzia and Helen Hastie. Supporting Exploratory Navigation for Runners Through Geographic Area Classification with Crowd-Sourced Data. In Proc. of the 17th International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI). Copenhagen, Denmark, 2015 (2015 acceptance rate: 25.2%). [pdf]

Dimitra Gkatzia and Saad Mahamood. A Snapshot of NLG Evaluation Practices 2005 – 2014. In Proc. of ENLG. Brighton, UK, 2015. [pdf] [data]

Dimitra Gkatzia, Amanda Cercas Curry, Verena Rieser and Oliver Lemon. A game-based setup for data collection and task-based evaluation of uncertain information presentation. In Proc. of ENLG. Brighton, UK, 2015. [pdf] [Game]

Amanda Cercas Curry, Dimitra Gkatzia and Verena Rieser. Generating and Evaluating Landmark-Based Navigation Instructions in Virtual Environments. In Proc. of ENLG. Brighton, UK, 2015. [pdf]

2014

Dimitra Gkatzia, Helen Hastie and Oliver Lemon. Comparing Multi-label classification with Reinforcement Learning for Summarisation of Time-series data. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL). Baltimore, USA, 2014 (2014 acceptance rate: 26.2%). [pdf]
MULAN was used for the Multi-label classification.

Dimitra Gkatzia, Helen Hastie and Oliver Lemon. Finding Middle Ground? Multi-objective Natural Language Generation from time-series data. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Gothenburg, Sweden, 2014 (2014 acceptance rate: 23.1%). [pdf]

Dimitra Gkatzia, Helen Hastie and Oliver Lemon. Multi-adaptive Natural Language Generation using Principal Component Regression. In Proceedings of the 8th International Natural Language Generation Conference (INLG). Philadelphia, USA, 2014. [pdf]

Dimitra Gkatzia, Verena Rieser, Alexander McSporran, Alistair McGowan, Alasdair Mort and Michaela Dewar. Generating Verbal Descriptions from Medical Sensor Data: A Corpus Study on User Preferences.BCS Health Informatics Scotland. Glasgow, UK, 2014. [pdf] [ppt][data]

2013

Dimitra Gkatzia, Helen Hastie, Srinivasan Janarthanam and Oliver Lemon. Generating student feedback from time-series data using Reinforcement Learning. In Proceedings of the 14th European Workshop on Natural Language Generation (ENLG), Sofia, Bulgaria, 2013. [pdf]

2012

Dimitra Gkatzia and Helen Hastie. Dynamic user modelling for personalized report generation of time-series data. In Symposium on Influencing People with Information (SIPI). Aberdeen, Scotland, 2012. [pdf]

Non-referred

Dimitra Gkatzia. Predicting the Success of Referring Expressions of Objects in Real-World Images. RefNet Roundtable, Aberdeen, 2016. [pdf] [poster]

Dimitra Gkatzia and Helen Hastie. An Ensemble method for Content Selection for Data-to-text SystemsIn the 1st International workshop on Data-to-text Generation (D2T). Edinburgh, UK, 2015. [pdf]

Verena Rieser and Dimitra Gkatzia. Generation for Things Unknown: Accounting for First-Time Users and Hidden Scenes In the 1st International workshop on Data-to-text Generation (D2T). Edinburgh, UK, 2015. [pdf]

Dimitra Gkatzia. “Keep up the good work!” Generating Feedback for Students using Reinforcement Learning. In SICSA PhD Conference, Stirling, Scotland, 2013. [poster]

Talks

From the Virtual to the Real World: Referring to Objects in Spatial Real-World Images. September, 2015, IROS ’15 Workshop on Spatial Reasoning and Interaction for Real-World Robotics. Hamburg, Germany. [ppt]

Generation of Textual Descriptions from Medical Sensor Data for Unknown Users, November, 2014, Aalto University, Helsinki, Finland.

Multi-label Classification [ppt], Machine Learning Group, October, 2013, Heriot-Watt University, Edinburgh.

Summarisation from time-series data, PhD seminar talk, May, 2013, Heriot-Watt University, Edinburgh.

Natural Language Generation from Data [ppt], December, 2011, Heriot-Watt University, Edinburgh.

Advertisements