Paul Piwek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Paul Piwek has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
Helmut Prendinger
National Institute of Informatics
6 shared publicationsMitsuru Ishizuka
The University of Tokyo
5 shared publications- Jacopo Amidei
Universitat Oberta de Catalunya
4 shared publications Kees van Deemter
University of Aberdeen
3 shared publicationsRichard Power
The Open University
3 shared publicationsSvetlana Stoyanchev
3 shared publications
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 14099-14119
Coherence of Argumentative Dialogue Snippets: A New Method for Large Scale Evaluation with an Application to Inference Anchoring Theory
Paul Piwek, Jacopo Amidei, Svetlana Stoyanchev. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 14099-14119
Open AccessCoherence of Argumentative Dialogue Snippets: A New Method for Large Scale Evaluation with an Application to Inference Anchoring Theory
Paul Piwek, Jacopo Amidei, Svetlana Stoyanchev. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
Opening up Minds with Argumentative Dialogues
Recent research on argumentative dialogues has focused on persuading people to take some action, changing their stance on the topic of discussion, or winning debates. In this work, we focus on argumentative dialogues that aim to open up (rather than change) people's minds to help them become more understanding to views that are unfamiliar or in opposition to their own convictions. To this end, we present a dataset of 183 argumentative dialogues about 3 controversial topics: veganism, Brexit and COVID-19 vaccination. The dialogues were collected using the Wizard of Oz approach, where wizards leverage a knowledge-base of arguments to converse with participants. Open-mindedness is measured before and after engaging in the dialogue using a questionnaire from the psychology literature, and success of the dialogue is measured as the change in the participant's stance towards those who hold opinions different to theirs. We evaluate two dialogue models: a Wikipedia-based and an argument-based model. We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity.
Open AccessOpening up Minds with Argumentative Dialogues
Recent research on argumentative dialogues has focused on persuading people to take some action, changing their stance on the topic of discussion, or winning debates. In this work, we focus on argumentative dialogues that aim to open up (rather than change) people's minds to help them become more understanding to views that are unfamiliar or in opposition to their own convictions. To this end, we present a dataset of 183 argumentative dialogues about 3 controversial topics: veganism, Brexit and COVID-19 vaccination. The dialogues were collected using the Wizard of Oz approach, where wizards leverage a knowledge-base of arguments to converse with participants. Open-mindedness is measured before and after engaging in the dialogue using a questionnaire from the psychology literature, and success of the dialogue is measured as the change in the participant's stance towards those who hold opinions different to theirs. We evaluate two dialogue models: a Wikipedia-based and an argument-based model. We show that while both models perform closely in terms of opening up minds, the argument-based model is significantly better on other dialogue properties such as engagement and clarity.
- Open Access
- 26 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 494-499
Challenges with Learning to Program and Problem Solve
- 26 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 494-499
Open AccessChallenges with Learning to Program and Problem Solve
- Open Access
- 9 January 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Learning to program
- 9 January 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessLearning to program
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 344-354
Agreement is overrated: A plea for correlation to assess human evaluation reliability
Jacopo Amidei, Paul Piwek, Alistair Willis. Proceedings of the 12th International Conference on Natural Language Generation. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 344-354
Open AccessAgreement is overrated: A plea for correlation to assess human evaluation reliability
Jacopo Amidei, Paul Piwek, Alistair Willis. Proceedings of the 12th International Conference on Natural Language Generation. 2019.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 397-402
The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations
Jacopo Amidei, Paul Piwek, Alistair Willis. Proceedings of the 12th International Conference on Natural Language Generation. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 397-402
Open AccessThe use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations
Jacopo Amidei, Paul Piwek, Alistair Willis. Proceedings of the 12th International Conference on Natural Language Generation. 2019.
- Open Access
A syllogistic system for propositions with intermediate quantifiers
This paper describes a formalism that subsumes Peterson's intermediate quantifier syllogistic system, and extends the ideas by van Eijck on Aristotle's logic. Syllogisms are expressed in a concise form making use of and extending the Monotonicity Calculus. Contradictory and contrary relationships are added so that deduction can derive propositions expressing a form of negation.
Open AccessA syllogistic system for propositions with intermediate quantifiers
This paper describes a formalism that subsumes Peterson's intermediate quantifier syllogistic system, and extends the ideas by van Eijck on Aristotle's logic. Syllogisms are expressed in a concise form making use of and extending the Monotonicity Calculus. Contradictory and contrary relationships are added so that deduction can derive propositions expressing a form of negation.
- Open Access
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 307-317
Evaluation methodologies in Automatic Question Generation 2013-2018
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 307-317
Open AccessEvaluation methodologies in Automatic Question Generation 2013-2018
- Open Access
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
- p. 178-187
A model of suspense for narrative generation
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
- p. 178-187
Open AccessA model of suspense for narrative generation
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 212-216
Collecting Reliable Human Judgements on Machine-Generated Language: The Case of the QG-STEC Data
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
- p. 212-216
Collecting Reliable Human Judgements on Machine-Generated Language: The Case of the QG-STEC Data