Test set sampling affects system rankings: expanded human evaluation of WMT20 English-Inuktitut systems
We present a collection of expanded human annotations of the WMT20 English-Inuktitut machine translation shared task, covering the Nunavut Hansard portion of the dataset. Additionally, we recompute News rankings to take into account the completed set of human annotations and certain irregularities i...
| Main Authors: | , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | English |
| Published: |
Association for Computational Linguistics
2022
|
| Subjects: | |
| Online Access: | https://nrc-publications.canada.ca/eng/view/ft/?id=d52a4c28-7e45-48ef-a575-998fc349eeb8 https://nrc-publications.canada.ca/eng/view/object/?id=d52a4c28-7e45-48ef-a575-998fc349eeb8 https://nrc-publications.canada.ca/fra/voir/objet/?id=d52a4c28-7e45-48ef-a575-998fc349eeb8 |
| Summary: | We present a collection of expanded human annotations of the WMT20 English-Inuktitut machine translation shared task, covering the Nunavut Hansard portion of the dataset. Additionally, we recompute News rankings to take into account the completed set of human annotations and certain irregularities in the annotation task construction. We show the effect of these changes on the downstream task of the evaluation of automatic metrics. Finally, we demonstrate that character-level metrics correlate well with human judgments for the task of automatically evaluating translation into this polysynthetic language. Peer reviewed: Yes NRC publication: Yes |
|---|