Point at the triple: Generation of text summaries from knowledge base triples (Extended Abstract)
Point at the triple: Generation of text summaries from knowledge base triples (Extended Abstract)
We investigate the problem of generating natural language summaries from knowledge base triples. Our approach is based on a pointer-generator net- work, which, in addition to generating regular words from a fixed target vocabulary, is able to ver- balise triples in several ways. We undertake an au- tomatic and a human evaluation on single and open- domain summaries generation tasks. Both show that our approach significantly outperforms other data-driven baselines.
International Joint Conferences on Artificial Intelligence
Vougiouklis, Pavlos
1a3a5de1-b558-4715-a6dd-9117a48e9521
Maddalena, Eddy
397dbaba-4363-4c11-8e52-4a7ba4df4bae
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Simperl, Elena
40261ae4-c58c-48e4-b78b-5187b10e4f67
Vougiouklis, Pavlos
1a3a5de1-b558-4715-a6dd-9117a48e9521
Maddalena, Eddy
397dbaba-4363-4c11-8e52-4a7ba4df4bae
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Simperl, Elena
40261ae4-c58c-48e4-b78b-5187b10e4f67
Vougiouklis, Pavlos, Maddalena, Eddy, Hare, Jonathon and Simperl, Elena
(2020)
Point at the triple: Generation of text summaries from knowledge base triples (Extended Abstract).
In Proceedings of IJCAI-PRICAI 2020 Journal Track.
International Joint Conferences on Artificial Intelligence..
(In Press)
Record type:
Conference or Workshop Item
(Paper)
Abstract
We investigate the problem of generating natural language summaries from knowledge base triples. Our approach is based on a pointer-generator net- work, which, in addition to generating regular words from a fixed target vocabulary, is able to ver- balise triples in several ways. We undertake an au- tomatic and a human evaluation on single and open- domain summaries generation tasks. Both show that our approach significantly outperforms other data-driven baselines.
Text
main
- Accepted Manuscript
More information
Accepted/In Press date: 25 May 2020
Venue - Dates:
International Joint Conference on Artificial Intelligence - Pacific Rim International Conference on Artificial Intelligence, 2020-07-11 - 2020-07-17
Identifiers
Local EPrints ID: 441976
URI: http://eprints.soton.ac.uk/id/eprint/441976
PURE UUID: 86f3c1b6-06cf-47fb-a2e7-9de26f1531be
Catalogue record
Date deposited: 03 Jul 2020 16:30
Last modified: 17 Mar 2024 05:41
Export record
Contributors
Author:
Pavlos Vougiouklis
Author:
Jonathon Hare
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics