Abstract
We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data. We put forth and evaluate two dictionary-based metrics. On the tasks of accuracy prediction and system ranking, we reveal that these metrics are reliable enough to approximate test set-based evaluation, and at the same time lean enough to support assessment for truly low-resource languages.- Anthology ID:
- E17-2040
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 248–253
- Language:
- URL:
- https://aclanthology.org/E17-2040
- DOI:
- Cite (ACL):
- Željko Agić, Barbara Plank, and Anders Søgaard. 2017. Cross-lingual tagger evaluation without test data. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 248–253, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Cross-lingual tagger evaluation without test data (Agić et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/E17-2040.pdf