Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System

TL;DR

This paper explores a multilingual data-to-text generation approach using NMT for translating grammatical configurations, combined with a cross-language grammar model and human review, demonstrating effective performance on a basketball dataset.

Contribution

The paper introduces a rule-based NLG system with NMT translation and a cross-language grammar model, enabling scalable, human-reviewed multilingual text generation from data.

Findings

System performs well on basketball dataset

Grammatical correctness in translation tasks

Scales without human in the loop

Abstract

One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in document planning stages to generate output. In this paper, we describe a rule-based NLG implementation of this approach where the configuration is translated by Neural Machine Translation (NMT) combined with a one-time human review, and introduce a cross-language grammar dependency model to create a multilingual NLG system that generates text from the source data, scaling the generation phase without a human in the loop. Additionally, we introduce a method for human post-editing evaluation on the automatically translated text. Our evaluation on the SportSett:Basketball dataset shows that our NLG system performs well, underlining its grammatical correctness in translation tasks.