Papers › Machine Translation Pre-training for Data-to-Text Generation -- A Case Study in Czech
Machine Translation Pre-training for Data-to-Text Generation -- A Case Study in Czech
Mihir Kale, Scott Roy
While there is a large body of research studying deep learning methods for text generation from structured data, almost all of it focuses purely on English. In this paper, we study the effectiveness of machine translation based pre-training for data-to-text generation in non-English languages. Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems. Moreover, since data-to-text corpora are typically small, this task can benefit greatly from pre-training. Based on our experiments on Czech, a morphologically complex language, we find that pre-training lets us train end-to-end models with significantly improved performance, as judged by automatic metrics and human evaluation. We also show that this approach enjoys several desirable properties, including improved performance in low data scenarios and robustness to unseen slot values.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Data-to-Text Generation | Czech Restaurant NLG | binmt | BLEU score | 26.35 | #1 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | binmt | CIDER | 2.60 | #1 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | binmt | METEOR | 25.81 | #1 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | binmt | NIST | 5.24 | #1 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | mass | BLEU score | 17.72 | #3 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | mass | CIDER | 1.75 | #3 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | mass | METEOR | 21.16 | #3 of 3 | Archive leaderboard | report |
| Data-to-Text Generation | Czech Restaurant NLG | mass | NIST | 4.22 | #3 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections