# Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks

arXiv: https://arxiv.org/abs/1610.07796 · HTML: https://mlsanity.com/paper/1610.07796/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2016.

## Built on by (most cited first, 6 of 6)

- [Neural OCR Post-Hoc Correction of Historical Corpora](https://mlsanity.com/paper/2102.00583/) (2021)
- [Lexically Aware Semi-Supervised Learning for OCR Post-Correction](https://mlsanity.com/paper/2111.02622/) (2021)
- [A Benchmark and Dataset for Post-OCR text correction in Sanskrit](https://mlsanity.com/paper/2211.07980/) (2022)
- [Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling](https://mlsanity.com/paper/2105.11872/) (2021)
- [Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models](https://mlsanity.com/paper/2109.06264/) (2021)
- [Reducing Sequence Length by Predicting Edit Operations with Large Language Models](https://mlsanity.com/paper/2305.11862/) (2023)

## Abstract (arXiv)

We analyze the performance of encoder-decoder neural models and compare them with well-known established methods. The latter represent different classes of traditional approaches that are applied to the monotone sequence-to-sequence tasks OCR post-correction, spelling correction, grapheme-to-phoneme conversion, and lemmatization. Such tasks are of practical relevance for various higher-level research fields including digital humanities, automatic text correction, and speech recognition. We investigate how well generic deep-learning approaches adapt to these tasks, and how they perform in comparison with established and more specialized methods, including our own adaptation of pruned CRFs.