Papers with competitor models

2 papers
Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach: They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome: The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.
Confusionset-guided Pointer Networks for Chinese Spelling Check (P19-1)

Copied to clipboard

Challenge: Existing methods to detect and fix errors in Chinese are limited due to context.
Approach: They propose a Confusionset-guided pointer network for Chinese Spell Check task . they propose to use off-the-shelf confusionset to guide character generation .
Outcome: The proposed model outperforms all competitor models on three human-annotated datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations