Underreporting of errors in NLG output, and what to do about it

E Van Miltenburg, MA Clinciu, O Dušek… - arXiv preprint arXiv …, 2021 - arxiv.org
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 …

An experimental study measuring human annotator categorization agreement on commonsense sentences

H Santos, M Kejriwal, AM Mulvehill, G Forbush… - Experimental …, 2021 - cambridge.org
Developing agents capable of commonsense reasoning is an important goal in Artificial
Intelligence (AI) research. Because commonsense is broadly defined, a computational …

Task2dial: A novel task and dataset for commonsense enhanced task-based dialogue grounded in documents

C Strathearn, D Gkatzia - arXiv preprint arXiv:2204.01061, 2022 - arxiv.org
This paper proposes a novel task on commonsense-enhanced task-based dialogue
grounded in documents and describes the Task2Dial dataset, a novel dataset of document …

The Task2Dial dataset: A novel dataset for commonsense-enhanced task-based dialogue grounded in documents

C Strathearn, D Gkatzia - 2021 - napier-repository.worktribe.com
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 …

A Commonsense-Enhanced Document-Grounded Conversational Agent: A Case Study on Task-Based Dialogue

C Strathearn, D Gkatzia - Analysis and Application of Natural Language …, 2022 - Springer
This paper argues that future dialogue systems must retrieve relevant information from
multiple structured and unstructured data sources in order to generate natural and …