[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/aclbulk-2017-bollmann-learning-attention-historical-text-normalization/) [home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / Learning attention for historical text normalization by learning to pronounce # Learning attention for historical text normalization by learning to pronounce **Authors:** [Marcel Bollmann](https://md.mova.elamur.ai/free/en/docs/papers/authors/marcel-bollmann/), [Joachim Bingel](https://md.mova.elamur.ai/free/en/docs/papers/authors/joachim-bingel/) and [Anders Søgaard](https://md.mova.elamur.ai/free/en/docs/papers/authors/anders-sogaard/) · **Year:** 2017 · **Venue:** Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) **Link:** [aclanthology.org/P17-1031](https://aclanthology.org/P17-1031/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**31** citations](https://openalex.org/works?filter=cites:W2741138687) openalex-snapshot · 2026-10-14[**16** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/aclbulk-2017-bollmann-learning-attention-historical-text-normalization/) of the 140673 papers whose bibliographies we read[Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://aclanthology.org/volumes/P17-1/)[licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/P17-1031/) - [PDF](https://aclanthology.org/P17-1031.pdf) - [DOI 10.18653/v1/p17-1031](https://doi.org/10.18653/v1/p17-1031) - [OpenAlex](https://openalex.org/W2741138687) **Authors (3)** 1. [Marcel Bollmann](https://openalex.org/A5005438563) [ORCID](https://orcid.org/0000-0003-2598-8150) · [Semantic Scholar](https://www.semanticscholar.org/author/34887843) · h 11 · 318 citations · 42 works 2. [Joachim Bingel](https://openalex.org/A5028729586) [ORCID](https://orcid.org/0000-0002-4113-3390) · [Semantic Scholar](https://www.semanticscholar.org/author/3053695) · h 15 · 1225 citations · 33 works 3. [Anders Søgaard](https://openalex.org/A5018138946) [ORCID](https://orcid.org/0000-0001-5250-4276) · [Semantic Scholar](https://www.semanticscholar.org/author/1700187) · h 42 · 8345 citations · 438 works Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart. ## What it is about The paper treats historical normalisation as a character-level transduction with an encoder-decoder RNN, so no explicit character alignment is needed. A second task, grapheme-to-phoneme mapping of modern words, is used as auxiliary data for multi-task learning. The models are tested on 43 Anselm texts, using the first 1,000 tokens of each as the test set and 2,000 to 11,000 tokens for training. All encoder-decoder models beat Norma and the averaged perceptron, and the multi-task models beat the earlier bi-LSTM. Attention alone does not help, and it hurts the multi-task model. Of the 210.9 errors per test set made by the base model, attention fixes 47.7 and multi-task learning 45.4, and 27.7 of these fixes overlap. ## Ideas - I1. `en/src/morph.rs`: use a letter-to-sound key as a second check on candidate modern forms, built from the dictionary's pronunciations where available. A candidate must match the historical form on the sound-class key. Measure the candidate ranking accuracy on the test split of tools/gutenberg lessons. - I2. Overlap report in `en morph-eval`: count the items fixed by each of two methods and their overlap, as the paper does. This shows whether two rule sets fix the same errors before combining them. - I3. Position-wise counts: learn a character-to-character alignment table by counts, which is the transparent analogue of the attention weights, and measure word accuracy against the base rules on the same 1,000-token test sets. ## For Mova The chapter is [09. Early Modern and archaic forms](https://md.mova.elamur.ai/free/en/docs/languages/en/09-early-modern-and-archaic/). The code is `en/src/morph.rs` and `en morph-eval`. The paper's neural models are not for Mova; the sound-key and overlap ideas are the parts that can be built with counts and rules. English figures must come from our own lessons. ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/p17-1031](https://doi.org/10.18653/v1/p17-1031) ``` @inproceedings{bollmann2017learning, title = {{Learning attention for historical text normalization by learning to pronounce}}, author = {Bollmann, Marcel and Bingel, Joachim and Søgaard, Anders}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, year = {2017}, doi = {10.18653/v1/p17-1031}, url = {https://doi.org/10.18653/v1/p17-1031} } ``` - [← previous Different Flavors of GUM: Evaluating Genre and Sentence Type Effects on Multilayer Corpus Annotation Quality](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2016-zeldes-different-flavors-gum-evaluating-genre/) - [next → Improving a Strong Neural Parser with Conjunction-Specific Features](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2017-ficler-improving-strong-neural-parser-conjunction/) - [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Mayce Al Azawi, Muhammad Zeshan Afzal, and Thomas M. Breuel. 2013. Normalizing historical orthography for OCR historical documents using LSTM. In Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing. ACM, pages 80–85. https://doi.org/10.1145/2501115.2501131. [↗](https://doi.org/10.1145/2501115.2501131)