David M. Howcroft — accepted AI-conference papers

2021

OTTers: One-turn Topic Transitions for Open-Domain Dialogue

Karin Sevegnani, David M. Howcroft, Ioannis Konstas, Verena Rieser

ACL 2021long

Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task explores how a system connects two topics in a cooperative and coherent manner. The goal of the task is to generate a “bridging” utterance connecting the new topic to t…

Cited by 47 Source ↗PDF ↗code ↗Scholar ↗

2021

What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think

David M. Howcroft, Verena Rieser

EMNLP 2021main

Previous work has shown that human evaluations in NLP are notoriously under-powered. Here, we argue that there are two common factors which make this problem even worse: NLP studies usually (a) treat ordinal data as interval data and (b) operate under high variance settings while the differences the…

Cited by 27 Source ↗PDF ↗Scholar ↗