E
Emiel van Miltenburg
Researcher at Tilburg University
Publications - 34
Citations - 747
Emiel van Miltenburg is an academic researcher from Tilburg University. The author has contributed to research in topics: Natural language generation & Computer science. The author has an hindex of 11, co-authored 30 publications receiving 445 citations. Previous affiliations of Emiel van Miltenburg include VU University Amsterdam.
Papers
More filters
Proceedings ArticleDOI
Best practices for the human evaluation of automatically generated text
TL;DR: This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature, for Natural Language Generation systems.
Proceedings Article
Twenty Years of Confusion in Human Evaluation : NLG Needs Evaluation Sheets and Standardised Definitions
David M. Howcroft,Anya Belz,Miruna-Adriana Clinciu,Dimitra Gkatzia,Sadid A. Hasan,Saad Mahamood,Simon Mille,Emiel van Miltenburg,Sashank Santhanam,Verena Rieser +9 more
TL;DR: Due to a pervasive lack of clarity in reports and extreme diversity in approaches, human evaluation in NLG presents as extremely confused in 2020, and that the field is in urgent need of standard methods and terminology.
Journal ArticleDOI
Human evaluation of automatically generated text: Current trends and best practice guidelines
TL;DR: An overview of how (mostly intrinsic) human evaluation is currently conducted is provided and a set of best practices are presented, grounded in the literature, linked to the stages that researchers go through when conducting an evaluation research.
Posted Content
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
TL;DR: Automatic and human evaluations together with a qualitative analysis suggest that having explicit intermediate steps in the generation process results in better texts than the ones generated by end-to-end approaches.
Stereotyping and bias in the flickr30k dataset
TL;DR: The authors presented some evidence against this assumption, and provided a list of biases and unwarranted inferences that can be found in the Flickr30K dataset, and discussed how to deal with stereotype-driven descriptions in future applications.