Abstract | ||
---|---|---|
We present a novel approach to grammatical error correction based on Alternating Structure Optimization. As part of our work, we introduce the NUS Corpus of Learner English (NUCLE), a fully annotated one million words corpus of learner English available for research purposes. We conduct an extensive evaluation for article and preposition errors using various feature sets. Our experiments show that our approach outperforms two baselines trained on non-learner text and learner text, respectively. Our approach also outperforms two commercial grammar checking software packages. |
Year | Venue | Keywords |
---|---|---|
2011 | ACL | novel approach,extensive evaluation,million words corpus,alternating structure optimization,learner text,structure optimization,nus corpus,non-learner text,learner english,grammatical error correction,commercial grammar checking software,error correction |
Field | DocType | Volume |
Computer science,Speech recognition,Grammar,Error detection and correction,Software,Natural language processing,Artificial intelligence,Machine learning | Conference | P11-1 |
Citations | PageRank | References |
44 | 1.65 | 21 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Dahlmeier | 1 | 460 | 29.67 |
Hwee Tou Ng | 2 | 4092 | 300.40 |