Describing a Knowledge Base
Preprint
Abstract
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB). We build our generation framework based on a pointer network which can copy facts from the input KB, and add two attention mechanisms: (i) slot-aware attention to capture the association between a slot type and its corresponding slot value; and (ii) a new \emph{table position self-attention} to capture the inter-dependencies among related slots. For evaluation, besides standard metrics including BLEU, METEOR, and ROUGE, we propose a KB reconstruction based metric by extracting a KB from the generation output and comparing it with the input KB. We also create a new data set which includes 106,216 pairs of structured KBs and their corresponding natural language descriptions for two distinct entity types. Experiments show that our approach significantly outperforms state-of-the-art methods. The reconstructed KB achieves 68.8% - 72.6% F-score.Keywords
All Related Versions
- Version 1, 2018-09-06, ArXiv
- Version 2, 2018-09-30, ArXiv
- Published version: , 10.
This publication has 8 references indexed in Scilit:
- Learning Structured Text RepresentationsTransactions of the Association for Computational Linguistics, 2018
- A Graph-to-Sequence Model for AMR-to-Text Generation2018
- Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata2018
- Statistical Natural Language Generation from Tabular Non-textual Data2016
- Natural Language Generation in the context of the Semantic WebSemantic Web: – Interoperability, Usability, Applicability, 2014
- Learning Where to Attend with Deep Architectures for Image TrackingNeural Computation, 2012
- Automatic generation of weather forecast texts using comprehensive probabilistic generation-space modelsNatural Language Engineering, 2008
- Natural Language Generation in Health CareJournal of the American Medical Informatics Association, 1997