Mova0.5 pre-release⌕
☰
home / docs / papers / English / Historical Text Normalization with Delayed Rewards

Historical Text Normalization with Delayed Rewards

What it is about

Sequence-to-sequence normalisers are usually trained with token-level maximum likelihood. The paper fine-tunes such a model with policy gradient, so that the training signal is the exact match of the whole normalisation, a delayed reward. Six historical datasets are used. Fine-tuning reduces the error by 20% for English. For German, Hungarian, Icelandic, Slovene and Swedish the reduction is 7% to 16%, still significant at p < 0.01. The gains are largest for long words, for unseen words and for inputs where the baseline tends to produce long outputs. Inputs that stay unchanged over time are handled less well for English.

Ideas

For Mova

The chapter is 09. Early Modern and archaic forms. The code is en/src/morph.rs and en morph-eval. The paper's neural method is not for Mova; the exact-match reward is the idea to copy in a count-based form. Measure first the error rate of archaic split by word length.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1157

@inproceedings{flachs2019historical,
  title = {{Historical Text Normalization with Delayed Rewards}},
  author = {Flachs, Simon and Bollmann, Marcel and Søgaard, Anders},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1157},
  url = {https://doi.org/10.18653/v1/p19-1157}
}

References

21 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. ↗
  2. Lukas Balles, Javier Romero, and Philipp Hennig. 2017. Coupling adaptive batch sizes with learning rates. In Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence (UAI). find
  3. Marcel Bollmann. 2018. Normalization of historical texts with neural network models. Bochumer Linguistische Arbeitsberichte, 22. find
  4. Marcel Bollmann. 2019. A large-scale comparison of historical text normalization systems. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3885–3898. Association for Computational Linguistics. find our card
  5. Marcel Bollmann, Joachim Bingel, and Anders Søgaard. 2017. Learning attention for historical text normalization by learning to pronounce. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 332–344, Vancouver, Canada. Association for Computational Linguistics. find our card
  6. Marcel Bollmann and Anders Søgaard. 2016. Improving historical spelling normalization with bidirectional LSTMs and multi-task learning. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 131–139, Osaka, Japan. find
  7. The COL-ING 2016 Organizing Committee. find
  8. William W. Cohen, Pradeep Ravikumar, and Stephen E. Fienberg. 2003. A comparison of string metrics for matching names and records. In KDD Workshop on Data Cleaning and Object Consolidation. find
  9. Andrej Karpathy. 2016. Deep reinforcement learning: Pong from pixels. Retrieved on 21-10-2017. find
  10. Nikola Ljubešić, Katja Zupan, Darja Fišer, and Tomaž Erjavec. 2016. Normalising Slovene data: historical texts vs. user-generated content. In Proceedings of the 13th Conference on Natural Language Processing (KONVENS 2016), volume 16 of Bochumer Linguistische Arbeitsberichte, pages 146–155, Bochum, Germany. find
  11. Andriy Mnih and Karol Gregor. 2014. Neural variational inference and learning in belief networks. In Proceedings of the 31st International Conference on Machine Learning, volume 32 of Proceedings of Machine Learning Research, pages 1791–1799, Bejing, China. PMLR. find
  12. Eva Pettersson. 2016. Spelling Normalisation and Linguistic Analysis of Historical Text for Information Extraction. Doctoral dissertation, Uppsala University, Department of Linguistics and Philology, Uppsala. find
  13. Michael Piotrowski. 2012. Natural Language Processing for Historical Texts. Number 17 in Synthesis Lectures on Human Language Technologies. Morgan & Claypool. find
  14. Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2016. Sequence level training with recurrent neural networks. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2–4, 2016, Conference Track Proceedings. find
  15. Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2016. Minimum risk training for neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1683–1692, Berlin, Germany. Association for Computational Linguistics. find
  16. Samuel L. Smith and Quoc V. Le. 2018. A Bayesian perspective on generalization and stochastic gradient descent. In International Conference on Learning Representations. find
  17. Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. In Proceedings of the 12th International Conference on Neural Information Processing Systems, NIPS’99, pages 1057–1063, Cambridge, MA, USA. MIT Press. find
  18. Gongbo Tang, Fabienne Cap, Eva Pettersson, and Joakim Nivre. 2018. An evaluation of neural machine translation models on historical spelling normalization. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1320–1331, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  19. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30, pages 5998–6008. Curran Associates, Inc. find
  20. Lex Weaver and Nigel Tao. 2001. The optimal reward baseline for gradient-based reinforcement learning. In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI). find
  21. Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3):229–256. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/acl-2019-flachs-historical-text-normalization-delayed-rewards/