Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)

Pavlos Vougiouklis, Eddy Maddalena, Jonathon S. Hare, Elena Simperl

IJCAI 2020 pp. 5080-5084

doi:10.24963/IJCAI.2020/711 /ijcai/2020/vougiouklis2020ijcai-point/

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.

PDF IJCAI Semantic Scholar

Cite

Text

Vougiouklis et al. "Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/711

Markdown

[Vougiouklis et al. "Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/vougiouklis2020ijcai-point/) doi:10.24963/IJCAI.2020/711

BibTeX

@inproceedings{vougiouklis2020ijcai-point,
  title     = {{Point at the Triple: Generation of Text Summaries from Knowledge Base Triples (Extended Abstract)}},
  author    = {Vougiouklis, Pavlos and Maddalena, Eddy and Hare, Jonathon S. and Simperl, Elena},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {5080-5084},
  doi       = {10.24963/IJCAI.2020/711},
  url       = {https://mlanthology.org/ijcai/2020/vougiouklis2020ijcai-point/}
}