GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data
A knowledge base is a large repository of facts that are mainly represented as RDF triples, each of which consists of a subject, a predicate (relationship), and an object. The RDF triple representation offers a simple interface for applications to access the facts. However, this representation is not in a natural language form, which is difficult for humans to understand. We address this problem by proposing a system to translate a set of RDF triples into natural sentences based on an encoder-decoder framework. To preserve as much information from RDF triples as possible, we propose a novel graph-based triple encoder. The proposed encoder encodes not only the elements of the triples but also the relationships both within a triple and between the triples. Experimental results show that the proposed encoder achieves a consistent improvement over the baseline models by up to 17.6{\%}, 6.0{\%}, and 16.4{\%} in three common metrics BLEU, METEOR, and TER, respectively.
PDF Abstract
Datasets
WebNLG
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Data-to-Text Generation | WebNLG | GTR-LSTM (entity masking) | BLEU | 58.6 | # 12 |
