natural-language-processing-5

Spelling Correction

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in spelling-correction-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find spelling-correction-5 models and implementations

Datasets

GitHub Typo Corpus

Viwiki-Spelling

Subtasks

No subtasks available.

Most implemented papers

An Actor-Critic Algorithm for Sequence Prediction

Joelle Pineau, Anirudh Goyal, Yoshua Bengio, Aaron C. Courville, Kelvin Xu, Ryan Lowe, Dzmitry Bahdanau, Philemon Brakel•Sat Jul 23 2016

An approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL) that condition the critic network on the ground-truth output, and shows that this method leads to improved performance on both a synthetic task, and for German-English machine translation.

661

Content

0

Paper Graph

MoNoise: Modeling Noise Using a Modular Normalization System

Rob van der Goot, Gertjan van Noord•Mon Oct 09 2017

MoNoise is a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable, based on a modular candidate generation in which each module is responsible for a different type of normalization action.

37 0

Paper Graph

Robust to Noise Models in Natural Language Processing Tasks

Valentin Malykh•Sun Jun 30 2019

This work proposes robust to noise word embeddings model, which outperforms existing commonly used models, like fasttext and word2vec in different tasks, and investigates the noise robustness of current models in different natural language processing tasks.

11 0

Paper Graph

Tokenization Repair in the Presence of Spelling Errors

Hannah Bast, Matthias Hertel, M. Mohamed•Wed Oct 14 2020

This work identifies 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.

6 0

Paper Graph

A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser Ney Smoothing

Steffen Staab, Rene Pickhardt, Thomas Gottron, Martin Körner, P. Wagner, Till Speicher•Sat Apr 12 2014

A novel approach based on a systematic, recursive exploration of skip n-gram models which are interpolated using modified Kneser-Ney smoothing is introduced which generalizes language models as it contains the classical interpolation with lower order models as a special case.

28 0

Paper Graph

Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network

Keisuke Sakaguchi, Matt Post, Kevin Duh, Benjamin Van Durme•Sun Jul 31 2016

Inspired by the findings from the Cmabrigde Uinervtisy effect, a word recognition model based on a semi-character level recurrent neural network (scRNN) is proposed that has significantly more robust performance in word spelling correction compared to existing spelling checkers and character-based convolutional neural network.

96 0

Paper Graph

Kyoto University Participation to WAT 2016

Toshiaki Nakazawa, Chenhui Chu, S. Kurohashi, Fabien Cromierès•Wed Nov 30 2016

The approaches and results on the WAT 2016 shared translation tasks were described, which tried to use both an example-based machine translation (MT) system and a neural MT system.

24 0

Paper Graph

Systematically Adapting Machine Translation for Grammatical Error Correction

Courtney Napoles, Chris Callison-Burch•Thu Aug 31 2017

This work adapts machine translation to grammatical error correction, identifying how components of the statistical MT pipeline can be modified for this task and analyzing how each modification impacts system performance.

27 0

Paper Graph

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

Walter Daelemans, Simon Suster, Pieter Fivez•Wed Oct 18 2017

An unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings that generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context.

25 0

Paper Graph

Adding a benchmark result helps the community track progress.