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

Pavlos Vougiouklis, Eddy Maddalena, Jonathon Hare, Elena Simperl
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
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.
doi:10.24963/ijcai.2020/699 dblp:conf/ijcai/Ben-PoratKHERT20 fatcat:hszj5j4xhzcidoyo7wv5adcf4q