arXiv Open Access 2025

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

Andreas Madsack Johanna Heininger Adela Schneider Ching-Yi Chen Christian Eckard +1 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (6)

A

Andreas Madsack

J

Johanna Heininger

A

Adela Schneider

C

Ching-Yi Chen

C

Christian Eckard

R

Robert Weißgraeber

Format Sitasi

Madsack, A., Heininger, J., Schneider, A., Chen, C., Eckard, C., Weißgraeber, R. (2025). Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System. https://arxiv.org/abs/2501.16135

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓