Spelling Correction

42 papers with code • 0 benchmarks • 4 datasets

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

Most implemented papers

An Actor-Critic Algorithm for Sequence Prediction

rizar/actor-critic-public 24 Jul 2016

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL).

MoNoise: Modeling Noise Using a Modular Normalization System

robvanderg/monoise 10 Oct 2017

We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.

Robust to Noise Models in Natural Language Processing Tasks

madrugado/robust-w2v ACL 2019

There are a lot of noise texts surrounding a person in modern life.

Tokenization Repair in the Presence of Spelling Errors

ad-freiburg/tokenization-repair CoNLL (EMNLP) 2021

We identify three key ingredients of high-quality tokenization repair, all missing from previous work: deep language models with a bidirectional component, training the models on text with spelling errors, and making use of the space information already present.

An Extended Sequence Tagging Vocabulary for Grammatical Error Correction

wolfgarbe/symspell 12 Feb 2023

We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms.

Chinese Spelling Correction as Rephrasing Language Model

gingasan/lemon 17 Aug 2023

However, we note a critical flaw in the process of tagging one character to another, that the correction is excessively conditioned on the error.

Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network

simonroquette/CORAP 7 Aug 2016

Inspired by the findings from the Cmabrigde Uinervtisy effect, we propose a word recognition model based on a semi-character level recurrent neural network (scRNN).

Kyoto University Participation to WAT 2016

fabiencro/knmt WS 2016

We report very good translation results, especially when using neural MT for Chinese-to-Japanese translation.