IJCAI 2020poster0 citations
Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)
Pavlos Vougiouklis, Eddy Maddalena, Jonathon Hare, Elena Simperl
Abstract
We investigate the problem of generating natural language summaries from knowledge base triples. Our approach is based on a pointer-generator network, which, in addition to generating regular words from a fixed target vocabulary, is able to verbalise triples in several ways. We undertake an automatic and a human evaluation on single and open-domain summaries generation tasks. Both show that our approach significantly outperforms other data-driven baselines.
Natural Language Processing: Natural Language GenerationMachine Learning: Deep Generative ModelsMachine Learning: Knowledge-based Learning
BibTeX
@inproceedings{ijcai2020p711,
title = {Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)},
author = {Vougiouklis, Pavlos and Maddalena, Eddy and Hare, Jonathon and Simperl, Elena},
booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on
Artificial Intelligence, {IJCAI-20}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Christian Bessiere},
pages = {5080--5084},
year = {2020},
month = {7},
note = {Journal track},
doi = {10.24963/ijcai.2020/711},
url = {https://doi.org/10.24963/ijcai.2020/711},
}