conference-paper
Open access
Evaluating Metrics for Document-context Evaluation in Machine Translation
Research footprint
At a glance
- Citations
- 2
- References
- 6
- Comments
- 0
Paper overview
Abstract
We describe our submission of a new metric, SLIDE (Raunak et al., 2023), to the WMT 2023 metrics task.SLIDE is a reference-free qualityestimation metric that works by constructing a fixed sentence-length window over the documents in a test set, concatenating chunks and then sending them for scoring as a single unit by COMET (Rei et al., 2022a).We find that SLIDE improves dramatically over its contextless counterpart on the two WMT22 evaluation campaigns (MQM and DA+SQM).
Record transparency
Publication details
- DOI
- 10.18653/v1/2023.wmt-1.68
- OpenAlex
- W4389523918
- Document type
- conference-paper
- Language
- EN
- Last metadata update
Comments
Log in to join the discussion.