Skip to main content

Research Repository

Advanced Search

All Outputs (48)

Unveiling NLG Human-Evaluation Reproducibility: Lessons Learned and Key Insights from Participating in the ReproNLP Challenge (2023)
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 about the reproducibility of such evaluations have emerged, casting doubt on... Read More about Unveiling NLG Human-Evaluation Reproducibility: Lessons Learned and Key Insights from Participating in the ReproNLP Challenge.

TaskMaster: A Novel Cross-platform Task-based Spoken Dialogue System for Human-Robot Interaction (2023)
Conference Proceeding
Strathearn, C., Yu, Y., & Gkatzia, D. (2023). TaskMaster: A Novel Cross-platform Task-based Spoken Dialogue System for Human-Robot Interaction. In Proceedings of The Joint CUI and HRI Workshop at HRI 2023

The most effective way of communication between humans and robots is through natural language communication. However, there are many challenges to overcome before robots can effectively converse in order to collaborate and work together with humans.... Read More about TaskMaster: A Novel Cross-platform Task-based Spoken Dialogue System for Human-Robot Interaction.

Working with troubles and failures in conversation between humans and robots: workshop report (2023)
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 bring together a small, interdisciplinary group of researchers working on misc... Read More about Working with troubles and failures in conversation between humans and robots: workshop report.

Building a dual dataset of text-and image-grounded conversations and summarisation in Gàidhlig (Scottish Gaelic) (2023)
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 natural language generation (NLG) in particular. To address this gap, we deve... Read More about Building a dual dataset of text-and image-grounded conversations and summarisation in Gàidhlig (Scottish Gaelic).

enunlg: a Python library for reproducible neural data-to-text experimentation (2023)
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 post-processing and other implementation details. Diversity in implementatio... Read More about enunlg: a Python library for reproducible neural data-to-text experimentation.

LOWRECORP: the Low-Resource NLG Corpus Building Challenge (2023)
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 scarcity, we propose a novel challenge for the NLG community: low-resource languag... Read More about LOWRECORP: the Low-Resource NLG Corpus Building Challenge.

Edge NLP for Efficient Machine Translation in Low Connectivity Areas (2023)
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 natural language processing (NLP) aims to solve this problem by processing lan... Read More about Edge NLP for Efficient Machine Translation in Low Connectivity Areas.

Responsible Design & Evaluation of a Conversational Agent for a National Careers Service (2023)
Conference Proceeding
Wilson, M., Cruickshank, P., Gkatzia, D., & Robertson, P. (in press). Responsible Design & Evaluation of a Conversational Agent for a National Careers Service.

This PhD project applies a research-through-design approach to the development of a conversational agent for a national career service for young people. This includes addressing practical, interactional and ethical aspects of the system. For each asp... Read More about Responsible Design & Evaluation of a Conversational Agent for a National Careers Service.

Barriers and enabling factors for error analysis in NLG research (2023)
Journal Article
Van Miltenburg, E., Clinciu, M., Dušek, O., Gkatzia, D., Inglis, S., Leppänen, L., …Wen, L. (2023). Barriers and enabling factors for error analysis in NLG research. Northern European Journal of Language Technology, 9(1), https://doi.org/10.3384/nejlt.2000-1533.2023.4529

Earlier research has shown that few studies in Natural Language Generation (NLG) evaluate their system outputs using an error analysis, despite known limitations of automatic evaluation metrics and human ratings. This position paper takes the stance... Read More about Barriers and enabling factors for error analysis in NLG research.

Most NLG is Low-Resource: here's what we can do about it (2022)
Conference Proceeding
Howcroft, D. M., & Gkatzia, D. (2022). Most NLG is Low-Resource: here's what we can do about it. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM) (336-350)

Many domains and tasks in natural language generation (NLG) are inherently 'low-resource', where training data, tools and linguistic analyses are scarce. This poses a particular challenge to researchers and system developers in the era of machine-lea... Read More about Most NLG is Low-Resource: here's what we can do about it.

A Commonsense-Enhanced Document-Grounded Conversational Agent: A Case Study on Task-Based Dialogue (2022)
Book Chapter
Strathearn, C., & Gkatzia, D. (2023). A Commonsense-Enhanced Document-Grounded Conversational Agent: A Case Study on Task-Based Dialogue. In M. Abbas (Ed.), Analysis and Application of Natural Language and Speech Processing (123-144). Cham: Springer. https://doi.org/10.1007/978-3-031-11035-1_6

This paper argues that future dialogue systems must retrieve relevant information from multiple structured and unstructured data sources in order to generate natural and informative responses as well as exhibit commonsense capabilities and flexibilit... Read More about A Commonsense-Enhanced Document-Grounded Conversational Agent: A Case Study on Task-Based Dialogue.

Multi3Generation: Multi-task, Multilingual, Multi-Modal Language Generation (2022)
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 working on different aspects of language generation. This "metapaper" will serve... Read More about Multi3Generation: Multi-task, Multilingual, Multi-Modal Language Generation.

Opportunities and risks in the use of AI in career development practice (2022)
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 work and career development. This article explores the potential benefits a... Read More about Opportunities and risks in the use of AI in career development practice.

Underreporting of errors in NLG output, and what to do about it (2021)
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 indicator of where systems should still be improved. If authors only report overa... Read More about Underreporting of errors in NLG output, and what to do about it.

Chefbot: A Novel Framework for the Generation of Commonsense-enhanced Responses for Task-based Dialogue Systems (2021)
Conference Proceeding
Strathearn, C., & Gkatzia, D. (2021). Chefbot: A Novel Framework for the Generation of Commonsense-enhanced Responses for Task-based Dialogue Systems. In Proceedings of the 14th International Conference on Natural Language Generation (46-47)

Conversational systems aim to generate responses that are accurate, relevant and engaging, either through utilising neural end-to-end models or through slot filling. Human-to-human conversations are enhanced by not only the latest utterance of the in... Read More about Chefbot: A Novel Framework for the Generation of Commonsense-enhanced Responses for Task-based Dialogue Systems.

The Task2Dial Dataset: A Novel Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents (2021)
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 instructions to an Information Follower (IF) so that the latter can succes... Read More about The Task2Dial Dataset: A Novel Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents.

CAPE: Context-Aware Private Embeddings for Private Language Learning (2021)
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. However, obtaining text representations or embeddings using these models risks... Read More about CAPE: Context-Aware Private Embeddings for Private Language Learning.

The Task2Dial Dataset (2021)
Dataset
Gkatzia, D., & Strathearn, C. (2021). The Task2Dial Dataset. [Dataset]

URL: https://huggingface.co/datasets/cstrathe435/Task2Dial

It's Common Sense, isn't it? Demystifying Human Evaluations in Commonsense-enhanced NLG systems (2021)
Conference Proceeding
Mahamood, S., Clinciu, M., & Gkatzia, D. (2021). It's Common Sense, isn't it? Demystifying Human Evaluations in Commonsense-enhanced NLG systems. In Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval)

Common sense is an integral part of human cognition which allows us to make sound decisions , communicate effectively with others and interpret situations and utterances. Endowing AI systems with commonsense knowledge capabilities will help us get cl... Read More about It's Common Sense, isn't it? Demystifying Human Evaluations in Commonsense-enhanced NLG systems.