Historical Text Normalization with Delayed Rewards
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Oa-Historical Text Normalization with Delayed Rewards
Final published version, 309 KB, PDF document
Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models. Policy gradient training enables direct optimization for exact matches, and while the small datasets in historical text normalization are prohibitive of from-scratch reinforcement learning, we show that policy gradient fine-tuning leads to significant improvements across the board. Policy gradient training, in particular, leads to more accurate normalizations for long or unseen words
Original language | English |
---|---|
Title of host publication | Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics |
Publisher | Association for Computational Linguistics |
Publication date | 2019 |
Pages | 1614-1619 |
DOIs | |
Publication status | Published - 2019 |
Event | 57th Annual Meeting of the Association for Computational Linguistics - Florence, Italy Duration: 1 Jul 2019 → 1 Jul 2019 |
Conference
Conference | 57th Annual Meeting of the Association for Computational Linguistics |
---|---|
Land | Italy |
By | Florence, |
Periode | 01/07/2019 → 01/07/2019 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 239617712