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...
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...
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...
Underreporting of errors in NLG output, and what to do about it
Conference Proceeding
van Miltenburg, E., Clinciu, M., Dušek, O., Gkatzia, D., Inglis, S., Leppänen, L., …Wen, L. (2021)
Underreporting of errors in NLG output, and what to do about it. In Proceedings of the 14th International Conference on Natural Language Generation (140-153
We observe a severe under-reporting of the different kinds of errors that Natural Language Generation systems make. This is a problem, because mistakes are an important indica...
The Task2Dial Dataset: A Novel Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents
Conference Proceeding
Strathearn, C., & Gkatzia, D. (2021)
The Task2Dial Dataset: A Novel Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents. In Proceedings of The Fourth International Conference on Natural Language and Speech Processing (ICNLSP 2021) (242-251
This paper describes the Task2Dial dataset, a novel dataset of document-grounded task-based dialogues in the food preparation domain , where an Information Giver (IG) provides...
CAPE: Context-Aware Private Embeddings for Private Language Learning
Conference Proceeding
Plant, R., Gkatzia, D., & Giuffrida, V. (2021)
CAPE: Context-Aware Private Embeddings for Private Language Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (7970-7978
Neural language models have contributed to state-of-the-art results in a number of downstream applications including sentiment analysis, intent classification and others. Howe...