# Neural Networks for Text Correction and Completion in Keyboard Decoding

arXiv: https://arxiv.org/abs/1709.06429 · HTML: https://mlsanity.com/paper/1709.06429/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2017.

## Built on by (most cited first, 12 of 12)

- [Spelling Correction with Denoising Transformer](https://mlsanity.com/paper/2105.05977/) (2021)
- ["Train one, Classify one, Teach one" -- Cross-surgery transfer learning for surgical step recognition](https://mlsanity.com/paper/2102.12308/) (2021)
- [TouchInsight: Uncertainty-aware Rapid Touch and Text Input for Mixed Reality from Egocentric Vision](https://mlsanity.com/paper/2410.05940/) (2024)
- [TapType: Ten-finger text entry on everyday surfaces via Bayesian inference](https://mlsanity.com/paper/2410.06001/) (2024)
- [Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques](https://mlsanity.com/paper/2310.08101/) (2023)
- [Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts](https://mlsanity.com/paper/2307.16213/) (2023)
- [Optimizing the Neural Network Training for OCR Error Correction of Historical Hebrew Texts](https://mlsanity.com/paper/2307.16220/) (2023)
- [Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages](https://mlsanity.com/paper/2203.14049/) (2022)
- [Maps Search Misspelling Detection Leveraging Domain-Augmented Contextual Representations](https://mlsanity.com/paper/2108.06842/) (2021)
- [Adapting Transformer Language Models for Predictive Typing in Brain-Computer Interfaces](https://mlsanity.com/paper/2305.03819/) (2023)
- [Domain specificity and data efficiency in typo tolerant spell checkers: the case of search in online marketplaces](https://mlsanity.com/paper/2308.01976/) (2023)
- [A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance](https://mlsanity.com/paper/2407.17383/) (2024)

## Abstract (arXiv)

Despite the ubiquity of mobile and wearable text messaging applications, the problem of keyboard text decoding is not tackled sufficiently in the light of the enormous success of the deep learning Recurrent Neural Network (RNN) and Convolutional Neural Networks (CNN) for natural language understanding. In particular, considering that the keyboard decoders should operate on devices with memory and processor resource constraints, makes it challenging to deploy industrial scale deep neural network (DNN) models. This paper proposes a sequence-to-sequence neural attention network system for automatic text correction and completion. Given an erroneous sequence, our model encodes character level hidden representations and then decodes the revised sequence thus enabling auto-correction and completion. We achieve this by a combination of character level CNN and gated recurrent unit (GRU) encoder along with and a word level gated recurrent unit (GRU) attention decoder. Unlike traditional language models that learn from billions of words, our corpus size is only 12 million words; an order of magnitude smaller. The memory footprint of our learnt model for inference and prediction is also an order of magnitude smaller than the conventional language model based text decoders. We report baseline performance for neural keyboard decoders in such limited domain. Our models achieve a word level accuracy of 90% and a character error rate CER of 2.4% over the Twitter typo dataset. We present a novel dataset of noisy to corrected mappings by inducing the noise distribution from the Twitter data over the OpenSubtitles 2009 dataset; on which our model predicts with a word level accuracy of 98% and sequence accuracy of 68.9%. In our user study, our model achieved an average CER of 2.6% with the state-of-the-art non-neural touch-screen keyboard decoder at CER of 1.6%.