Abstract
We highlight several issues in the evaluation of historical text normalization systems that make it hard to tell how well these systems would actually work in practice—i.e., for new datasets or languages; in comparison to more naïve systems; or as a preprocessing step for downstream NLP tools. We illustrate these issues and exemplify our proposed evaluation practices by comparing two neural models against a naïve baseline system. We show that the neural models generalize well to unseen words in tests on five languages; nevertheless, they provide no clear benefit over the naïve baseline for downstream POS tagging of an English historical collection. We conclude that future work should include more rigorous evaluation, including both intrinsic and extrinsic measures where possible.- Anthology ID:
- N18-2113
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marilyn Walker, Heng Ji, Amanda Stent
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 720–725
- Language:
- URL:
- https://aclanthology.org/N18-2113
- DOI:
- 10.18653/v1/N18-2113
- Cite (ACL):
- Alexander Robertson and Sharon Goldwater. 2018. Evaluating Historical Text Normalization Systems: How Well Do They Generalize?. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 720–725, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Evaluating Historical Text Normalization Systems: How Well Do They Generalize? (Robertson & Goldwater, NAACL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/N18-2113.pdf