Seq2RDF: An End-to-end Application for Deriving Triples from Natural Language Text
Published in
International Workshop on the Semantic Web(2018)External Links:
TL
TL;DR
This work presents an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary and proposes an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings.
Abstract
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.
References5 items
1
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases
2
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
3
Exploiting Task-Oriented Resources to Learn Word Embeddings for Clinical Abbreviation Expansion
4
Sequence to Sequence Learning with Neural Networks
5