# Improving Structured Text Recognition with Regular Expression Biasing

arXiv: https://arxiv.org/abs/2111.06738 · HTML: https://mlsanity.com/paper/2111.06738/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 10 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [SCATTER: Selective Context Attentional Scene Text Recognizer](https://mlsanity.com/paper/2003.11288/) (2020)
- [Scene Text Recognition from Two-Dimensional Perspective](https://mlsanity.com/paper/1809.06508/) (2018)

## Built on by (most cited first, 2 of 2)

- [STEP -- Towards Structured Scene-Text Spotting](https://mlsanity.com/paper/2309.02356/) (2023)
- [Automated Extraction of Acronym-Expansion Pairs from Scientific Papers](https://mlsanity.com/paper/2412.01093/) (2024)

## Abstract (arXiv)

We study the problem of recognizing structured text, i.e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing. A biased recognizer recognizes text that matches the specified regexes with significantly improved accuracy, at the cost of a generally small degradation on other text. The biasing is realized by modeling regexes as a Weighted Finite-State Transducer (WFST) and injecting it into the decoder via dynamic replacement. A single hyperparameter controls the biasing strength. The method is useful for recognizing text lines with known formats or containing words from a domain vocabulary. Examples include driver license numbers, drug names in prescriptions, etc. We demonstrate the efficacy of regex biasing on datasets of printed and handwritten structured text and measures its side effects.