Detecting Errors in English Article Usage with a Maximum EntropyClassifier Trained on a Large, Diverse Corpus

4th International Conference on Language Resources and Evaluation

Na-Rae Han ; Martin Chodorow ; Claudia Leacock

PID  :  124061

来源: CEUR

【 摘 要 】

One of the most difficult challenges faced by nonnative speakers of English is mastering the system of English articles. We trained amaximum entropy classifier to select among a/an, the, or zero article for noun phrases, based on a set of features extracted from thelocal context of each.When the classifier was trained on 6 million noun phrases, its performance was correct about 88% of the time.We also used the classifier to detect article errors in the TOEFL essays of native speakers of Chinese, Japanese, and Russian.Agreement with human annotators was about 88% (kappa = 0.36). Many of the disagreements were due to the classifier s lack ofdiscourse information. Performance rose to 94% agreement (kappa = 0.47) when the system accepted noun phrases as correct in cases