Abstract
In this paper we propose the task of list verbalisation within a Knowledge Graph Question Answering system. Inspired by the Gricean Maxims of Quantity, Relation, and Manner we show a proof of concept ranking answer candidates through graph-based and language model-based measurements for on the one hand popularity and on the other hand a more pragmatically informed context. Our finding show that in our current set-up graph-based measures work best, while language model-based systems need further refinement and may benefit from approaches such as fine-tuning or prompting. We evaluate our approach with a user study and give insights into promising future directions of the task.
| Original language | English |
|---|---|
| Title of host publication | AI4LEGAL-KGSUM 2022 Artificial Intelligence Technologies for Legal Documents and Knowledge Graph Summarization 2022 |
| Subtitle of host publication | Joint Proceedings of the 3th International Workshop on Artificial Intelligence Technologies for Legal Documents (AI4LEGAL 2022) and the 1st International Workshop on Knowledge Graph Summarization (KGSum 2022) co-located with the 21st International Semantic Web Conference (ISWC 2022) Virtual Event, Hangzhou, China, October 23-24, 2022 |
| Editors | María Navas-Loro, Carlos Badenes-Olmedo, Manolis Koubarakis, Jose Luis Redondo-García, Sabrina Kirrane, Nandana Mihindukulasooriya, Ken Satoh, Maribel Acosta |
| Publisher | CEUR-WS.org |
| Pages | 136-146 |
| Number of pages | 11 |
| Publication status | Published - 2022 |
| Event | 3rd International Workshop on Artificial Intelligence Technologies for Legal Documents and the 1st International Workshop on Knowledge Graph Summarization, AI4LEGAL-KGSUM 2022 - Virtual, Hangzhou, China Duration: 23 Oct 2022 → 24 Oct 2022 |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR Workshop Proceedings |
| Volume | 3257 |
| ISSN (Print) | 1613-0073 |
Conference
| Conference | 3rd International Workshop on Artificial Intelligence Technologies for Legal Documents and the 1st International Workshop on Knowledge Graph Summarization, AI4LEGAL-KGSUM 2022 |
|---|---|
| Country/Territory | China |
| City | Virtual, Hangzhou |
| Period | 23/10/22 → 24/10/22 |
Bibliographical note
Funding Information:This research was funded by the Vrije Universiteit Amsterdam and the Netherlands Organisation for Scientific Research ?NWO) through the Hybrid Intelligence Centre via the Zwaartekracht grant ?024.004.022), and the Spinoza grant ?SPI 63-260) awarded to Piek Vossen. We would also like to thank the reviewers for their excellent feedback that enhanced this paper. All remaining errors are our own.
Publisher Copyright:
© 2022 Copyright for this paper by its authors.
Keywords
- Gricean maxims
- KGQA
- List verbalisation
- Ranking
- Summarisation
