Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency

TL;DR

This paper introduces a syntax-controlled KG-to-text generation method that optimizes description order and enhances semantic consistency, achieving state-of-the-art results on WebNLG and DART datasets.

Contribution

It proposes a data-driven approach to predict KG description order and incorporates syntactic and semantic regularization for improved text generation.

Findings

Achieves state-of-the-art performance on WebNLG and DART datasets.

Enhances semantic consistency between generated text and KG.

Optimizes description order prediction using supervision from captions.

Abstract

The knowledge graph (KG) stores a large amount of structural knowledge, while it is not easy for direct human understanding. Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at the same time, maintains semantic consistency between generated sentences and the KG. Existing KG-to-text generation methods phrase this task as a sequence-to-sequence generation task with linearized KG as input and consider the consistency issue of the generated texts and KG through a simple selection between decoded sentence word and KG node word at each time step. However, the linearized KG order is commonly obtained through a heuristic search without data-driven optimization. In this paper, we optimize the knowledge description order prediction under the order supervision extracted from the caption and further enhance the consistency of the generated sentences and KG through syntactic and semantic regularization. We incorporate the Part-of-Speech (POS) syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context when decoding each word in the generated sentence. Extensive experiments are conducted on two datasets, WebNLG and DART, and achieve state-of-the-art performances.