Spelling Correction

42 papers with code • 0 benchmarks • 4 datasets

Spelling correction is the task of detecting and correcting spelling mistakes.

Most implemented papers

SEARNN: Training RNNs with Global-Local Losses

RemiLeblond/SeaRNN-open ICLR 2018

We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction.

Systematically Adapting Machine Translation for Grammatical Error Correction

cnap/smt-for-gec WS 2017

Our model rivals the current state of the art using a fraction of the training data.

Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings

clips/clinspell 19 Oct 2017

We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings.

DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm Based on Learned High Dimensional Encoding

System-T/DimSim CONLL 2018

Phonetic similarity algorithms identify words and phrases with similar pronunciation which are used in many natural language processing tasks.

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors

mhagiwara/github-typo-corpus LREC 2020

The lack of large-scale datasets has been a major hindrance to the development of NLP tasks such as spelling correction and grammatical error correction (GEC).

Neural Chinese Word Segmentation as Sequence to Sequence Translation

SourcecodeSharing/CWSpostediting 29 Nov 2019

In this paper, we cast the CWS as a sequence translation problem and propose a novel sequence-to-sequence CWS model with an attention-based encoder-decoder framework.

Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Check

mnhng/HeadFilt 27 Aug 2020

Spell check is a useful application which processes noisy human-generated text.

NeuSpell: A Neural Spelling Correction Toolkit

neuspell/neuspell EMNLP 2020

We introduce NeuSpell, an open-source toolkit for spelling correction in English.

Context-aware Stand-alone Neural Spelling Correction

jacklxc/StandAloneSpellingCorrection Findings of the Association for Computational Linguistics 2020

Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings.