We present an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary. Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings. Our model learns the mapping from natural language text to triple representation in the form of subject-predicate-object using the selected knowledge graph vocabulary. Experiments on three different data sets show that we achieve competitive F1-Measures over the baselines using our simple yet effective approach. A demo video is included.
@article{arxiv.1807.01763,
title = {Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text},
author = {Yue Liu and Tongtao Zhang and Zhicheng Liang and Heng Ji and Deborah L. McGuinness},
journal= {arXiv preprint arXiv:1807.01763},
year = {2018}
}
Comments
Proceedings of the 17th International Semantic Web Conference P&D