Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.16135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917903619588096 |
|---|---|
| author | Madsack, Andreas Heininger, Johanna Schneider, Adela Chen, Ching-Yi Eckard, Christian Weißgraeber, Robert |
| author_facet | Madsack, Andreas Heininger, Johanna Schneider, Adela Chen, Ching-Yi Eckard, Christian Weißgraeber, Robert |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System Madsack, Andreas Heininger, Johanna Schneider, Adela Chen, Ching-Yi Eckard, Christian Weißgraeber, Robert Computation and Language 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. |
| title | Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.16135 |