# Domain specificity and data efficiency in typo tolerant spell checkers: the case of search in online marketplaces

arXiv: https://arxiv.org/abs/2308.01976 · HTML: https://mlsanity.com/paper/2308.01976/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [NeuSpell: A Neural Spelling Correction Toolkit](https://mlsanity.com/paper/2010.11085/) (2020)
- [GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors](https://mlsanity.com/paper/1911.12893/) (2019)
- [Neural Networks for Text Correction and Completion in Keyboard Decoding](https://mlsanity.com/paper/1709.06429/) (2017)
- [Wronging a Right: Generating Better Errors to Improve Grammatical Error Detection](https://mlsanity.com/paper/1810.00668/) (2018)
- [Correcting diacritics and typos with a ByT5 transformer model](https://mlsanity.com/paper/2201.13242/) (2022)
- [Correcting the Autocorrect: Context-Aware Typographical Error Correction via Training Data Augmentation](https://mlsanity.com/paper/2005.01158/) (2020)
- [EmbedJoin: Efficient Edit Similarity Joins via Embeddings](https://mlsanity.com/paper/1702.00093/) (2017)

## Abstract (arXiv)

Typographical errors are a major source of frustration for visitors of online marketplaces. Because of the domain-specific nature of these marketplaces and the very short queries users tend to search for, traditional spell cheking solutions do not perform well in correcting typos. We present a data augmentation method to address the lack of annotated typo data and train a recurrent neural network to learn context-limited domain-specific embeddings. Those embeddings are deployed in a real-time inferencing API for the Microsoft AppSource marketplace to find the closest match between a misspelled user query and the available product names. Our data efficient solution shows that controlled high quality synthetic data may be a powerful tool especially considering the current climate of large language models which rely on prohibitively huge and often uncontrolled datasets.