NABU $\mathrm{-}$ Multilingual Graph-based Neural RDF Verbalizer

TL;DR

NABU is a multilingual graph-based neural model that converts RDF data into natural language text in English, German, and Russian, outperforming existing models especially in English, and demonstrating the potential of knowledge graphs for multilingual text generation.

Contribution

This paper introduces NABU, the first multilingual graph-based neural RDF verbalizer that effectively generates text in three languages using a unified encoder-decoder architecture.

Findings

NABU outperforms state-of-the-art models on English RDF verbalization with 66.21 BLEU.

NABU achieves consistent multilingual performance with 56.04 BLEU across languages.

The model demonstrates the viability of using knowledge graphs for multilingual natural language generation.

Abstract

The RDF-to-text task has recently gained substantial attention due to continuous growth of Linked Data. In contrast to traditional pipeline models, recent studies have focused on neural models, which are now able to convert a set of RDF triples into text in an end-to-end style with promising results. However, English is the only language widely targeted. We address this research gap by presenting NABU, a multilingual graph-based neural model that verbalizes RDF data to German, Russian, and English. NABU is based on an encoder-decoder architecture, uses an encoder inspired by Graph Attention Networks and a Transformer as decoder. Our approach relies on the fact that knowledge graphs are language-agnostic and they hence can be used to generate multilingual text. We evaluate NABU in monolingual and multilingual settings on standard benchmarking WebNLG datasets. Our results show that NABU outperforms state-of-the-art approaches on English with 66.21 BLEU, and achieves consistent results across all languages on the multilingual scenario with 56.04 BLEU.