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...
From the Virtual to the RealWorld: Referring to Objects in Real-World Spatial Scenes
Conference Proceeding
Gkatzia, D., Rieser, V., Bartie, P., & Mackaness, W. (2015)
From the Virtual to the RealWorld: Referring to Objects in Real-World Spatial Scenes. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 1936-1942. https://doi.org/10.18653/v1/d15-1224
Predicting the success of referring expressions (RE) is vital for real world applications such as navigation systems. Traditionally, research has focused on studying Referring...
A Snapshot of NLG Evaluation Practices 2005 - 2014
Conference Proceeding
Gkatzia, D., & Mahamood, S. (2015)
A Snapshot of NLG Evaluation Practices 2005 - 2014. https://doi.org/10.18653/v1/w15-4708
In this paper we present a snapshot of endto-end NLG system evaluations as presented in conference and journal papers1 over the last ten years in order to better understand th...
A Game-Based Setup for Data Collection and Task-Based Evaluation of Uncertain Information Presentation
Conference Proceeding
Gkatzia, D., Cercas Curry, A., Rieser, V., & Lemon, O. (2015)
A Game-Based Setup for Data Collection and Task-Based Evaluation of Uncertain Information Presentation. In Proceedings of the 15th European Workshop on Natural Language Generation, 112-113. https://doi.org/10.18653/v1/w15-4720
Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores, such as probabilities. A concrete example of such data is weather data. We w...
Generating and Evaluating Landmark-Based Navigation Instructions in Virtual Environments
Conference Proceeding
Cercas Curry, A., Gkatzia, D., & Rieser, V. (2015)
Generating and Evaluating Landmark-Based Navigation Instructions in Virtual Environments. In Proceedings of the 15th European Workshop on Natural Language Generation, 90-94. https://doi.org/10.18653/v1/w15-4715
Referring to landmarks has been identified to lead to improved navigation instructions. However, a previous corpus study suggests that human “wizards” also choose to refer to ...
Comparing Multi-label Classification with Reinforcement Learning for Summarisation of Time-series Data
Conference Proceeding
Gkatzia, D., Hastie, H., & Lemon, O. (2014)
Comparing Multi-label Classification with Reinforcement Learning for Summarisation of Time-series Data. In Proceedings of the Conference Volume 1: Long Papers. , (1231-1240). https://doi.org/10.3115/v1/p14-1116
We present a novel approach for automatic report generation from time-series data, in the context of student feedback generation. Our proposed methodology treats content selec...