Abstract | ||
---|---|---|
In this paper, we propose a statistical model for detecting article errors, which Japanese learners of English often make in English writing. It is based on the three head words --- the verb head, the preposition, and the noun head. To overcome the data sparseness problem, we apply the backed-off estimate to it. Experiments show that its performance (F-measure=0.70) is better than that of other methods. Apart from the performance, it has two advantages: (i) Rules for detecting article errors are automatically generated as conditional probabilities once a corpus is given; (ii) Its recall and precision rates are adjustable. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1093/ietisy/e88-d.7.1700 | IEICE Transactions |
Keywords | Field | DocType |
english writing,article error,backed-off estimate,japanese learner,conditional probability,data sparseness problem,noun head,head word,precision rate,detecting article errors,verb head,head words,statistical model | Verb,Conditional probability,Computer science,Noun,Precision and recall,Speech recognition,Error detection and correction,Natural language,Natural language processing,Statistical model,Artificial intelligence | Journal |
Volume | Issue | ISSN |
E88-D | 7 | 0916-8532 |
Citations | PageRank | References |
1 | 0.36 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryo Nagata | 1 | 1 | 0.69 |
Tatsuya Iguchi | 2 | 2 | 1.10 |
Fumito Masui | 3 | 87 | 27.22 |
Atsuo Kawai | 4 | 42 | 6.95 |
Naoki Isu | 5 | 35 | 5.22 |