David M. Howcroft
David M. Howcroft
Home
Posts
Publications
Talks
Contact
Light
Dark
Automatic
paper-conference
Building a dual dataset of text- and image-grounded conversations and summarisation in Gàidhlig (Scottish Gaelic)
Gàidhlig (Scottish Gaelic; gd) is spoken by about 57k people in Scotland, but remains an under-resourced language with respect to …
David M. Howcroft
,
William Lamb
,
Anna Groundwater
,
Dimitra Gkatzia
DOI
ACL Anthology
enunlg: a Python library for reproducible neural data-to-text experimentation
Over the past decade, a variety of neural architectures for data-to-text generation (NLG) have been proposed. However, each system …
David M. Howcroft
,
Dimitra Gkatzia
DOI
ACL Anthology
LOWRECORP: the Low-Resource NLG Corpus Building Challenge
Most languages in the world do not have sufficient data available to develop neural-network-based natural language generation (NLG) …
Khyathi Raghavi Chandu
,
David M. Howcroft
,
Dimitra Gkatzia
,
Yi-Ling Chung
,
Yufang Hou
,
Chris Chinenye Emezue
,
Pawan Rajpoot
,
Tosin Adewumi
DOI
ACL Anthology
Most NLG is Low-Resource: here's what we can do about it
Many domains and tasks in natural language generation (NLG) are inherently ‘low-resource’, where training data, tools and linguistic …
David M. Howcroft
,
Dimitra Gkatzia
PDF
What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think
Previous work has shown that human evaluations in NLP are notoriously under-powered. Here, we argue that there are two common factors …
David M. Howcroft
,
Verena Rieser
PDF
Code
DOI
OTTers: One-turn Topic Transitions for Open-Domain Dialogue
Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task …
Karin Sevegnani
,
David M. Howcroft
,
Ioannis Konstas
,
Verena Rieser
PDF
Dataset
ACL Anthology
Twenty Years of Confusion in Human Evaluation: NLG Needs Evaluation Sheets and Standardised Definitions
Human assessment remains the most trusted forrm of evaluation in NLG, but highly diverse approaches and a proliferation of different …
David M. Howcroft
,
Anya Belz
,
Miruna Clinciu
,
Dimitra Gkatzia
,
Sadid A. Hasan
,
Saad Mahamood
,
Simon Mille
,
Emiel van Miltenburg
,
Sashank Santhanam
,
Verena Rieser
PDF
Dataset
Slides
ACL Anthology
Disentangling the Properties of Human Evaluation Methods: A Classification System to Support Comparability, Meta-Evaluation and Reproducibility Testing
Current standards for designing and reporting human evaluations in NLP mean it is generally unclear which evaluations are comparable …
Anya Belz
,
Simon Mille
,
David M. Howcroft
PDF
ACL Anthology
Semantic Noise Matters for Neural Natural Language Generation
Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to …
Ondřej Dušek
,
David M. Howcroft
,
Verena Rieser
PDF
Code
Poster
DOI
ACL Anthology
Appendix
Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning
Developing conventional natural language generation systems requires extensive attention from human experts in order to craft complex …
David M. Howcroft
,
Dietrich Klakow
,
Vera Demberg
PDF
Poster
DOI
ACL Anthology
»
Cite
×