Candidate re-ranking for SMT-based grammatical error correction Candidate re-ranking for SMT-based grammatical error correction
Paper summary They improve an existing error correction system by re-ranking its predictions. The basic approach uses machine translation to perform error correction on learner texts – the incorrect text is essentially translated into correct text. Here, they include a ranking SVM to score and reorder the n-best lists from the translation model. The reranking features include various internal scores from the translation model, the rank in the original ordering, language model probabilities trained on large corpora, language model scores based on only the n-best list, word-level translation probabilities, and sentence length features. They show improvement on two error correction datasets. https://i.imgur.com/RxAE11a.png Example output from the models.
aclweb.org
sci-hub
scholar.google.com
Candidate re-ranking for SMT-based grammatical error correction
Yuan, Zheng and Briscoe, Ted and Felice, Mariano
The Association for Computer Linguistics BEA@NAACL-HLT - 2016 via Local Bibsonomy
Keywords: dblp


Summary by Marek Rei 4 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and