GCP: Graph Encoder With Content-Planning for Sentence Generation From Knowledge Bases

Bayu Distiawan Trisedya, Jianzhong Qi, Wei Wang, Rui Zhang

Abstract

A knowledge base is a large repository of facts usually represented as triples, each consisting of a subject, a predicate, and an object. The triples together form a graph, i.e., a <i>knowledge graph</i> . The triple representation in a knowledge graph 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 triples (i.e., a graph) into natural sentences. We take an encoder-decoder based approach. Specifically, we propose a <i><b>G</b>raph encoder with</i> <b>C</b> <i>ontent-</i> <b>P</b> <i>lanning capability</i> ( <i>GCP</i> ) to encode an input graph. GCP not only works as an encoder but also serves as a content-planner by using an entity-order aware topological traversal to encode a graph. This way, GCP can capture the relationships between entities in a knowledge graph as well as providing information regarding the proper entity order for the decoder. Hence, the decoder can generate sentences with a proper entity mention ordering. Experimental results show that GCP achieves improvements over state-of-the-art models by up to <inline-formula><tex-math notation="LaTeX">$3.6\%$</tex-math></inline-formula> , <inline-formula><tex-math notation="LaTeX">$4.1\%$</tex-math></inline-formula> , and <inline-formula><tex-math notation="LaTeX">$3.8\%$</tex-math></inline-formula> in three common metrics BLEU, METEOR, and TER, respectively. The code is available at ( <uri>https://github.com/ruizhang-ai/GCP/</uri> )
BibTeX
@article{trisedya2022gcp,
  author = {Bayu Distiawan Trisedya and Jianzhong Qi and Wei Wang and Rui Zhang},
  title = {{GCP: Graph Encoder With Content-Planning for Sentence Generation From Knowledge Bases}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2022},
  doi = {10.1109/tpami.2021.3118703},
}

Loading related content...

Figure