Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.08870 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917001473032192 |
|---|---|
| author | Mrozinski, Krzysztof Kang, Minji Khota, Ahmed Sutanto, Vincent Michael De Giacomo, Giovanni Gatti |
| author_facet | Mrozinski, Krzysztof Kang, Minji Khota, Ahmed Sutanto, Vincent Michael De Giacomo, Giovanni Gatti |
| contents | Quality estimation (QE) reranking is a form of quality-aware decoding which aims to improve machine translation (MT) by scoring and selecting the best candidate from a pool of generated translations. While known to be effective at the sentence level, its application to the increasingly prominent domain of document-level translation remains underexplored. In this work, we evaluate QE reranking performance on document-level (rather than the typical sentence-level) translation, using various learned and large language model (LLM)-based QE metrics. We find that with our best learned metric, SLIDE, BLEURT-20 scores improve by +2.00 with only two candidates, and by +5.09 with 32, across both decoder-only LLM models and encoder-decoder neural machine translation (NMT) models. Using the best LLM-based metric, GEMBA-DA, gains of +1.63 and +4.30 are achieved under the same conditions. Although gains shrink with longer inputs, reranking with 32 candidates yields improvements of +2.34 (SLIDE) and +1.40 (GEMBA-DA) on our longest documents (512-1024 source tokens). These findings demonstrate the practical value of document-level QE, with minimal runtime overhead given suitable translation models and hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08870 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quality Estimation Reranking for Document-Level Translation Mrozinski, Krzysztof Kang, Minji Khota, Ahmed Sutanto, Vincent Michael De Giacomo, Giovanni Gatti Computation and Language Quality estimation (QE) reranking is a form of quality-aware decoding which aims to improve machine translation (MT) by scoring and selecting the best candidate from a pool of generated translations. While known to be effective at the sentence level, its application to the increasingly prominent domain of document-level translation remains underexplored. In this work, we evaluate QE reranking performance on document-level (rather than the typical sentence-level) translation, using various learned and large language model (LLM)-based QE metrics. We find that with our best learned metric, SLIDE, BLEURT-20 scores improve by +2.00 with only two candidates, and by +5.09 with 32, across both decoder-only LLM models and encoder-decoder neural machine translation (NMT) models. Using the best LLM-based metric, GEMBA-DA, gains of +1.63 and +4.30 are achieved under the same conditions. Although gains shrink with longer inputs, reranking with 32 candidates yields improvements of +2.34 (SLIDE) and +1.40 (GEMBA-DA) on our longest documents (512-1024 source tokens). These findings demonstrate the practical value of document-level QE, with minimal runtime overhead given suitable translation models and hardware. |
| title | Quality Estimation Reranking for Document-Level Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.08870 |