An analysis of grammatical errors in non-native speech in english

Abstract

While a wide variety of grammatical mistakes may be observed in the speech of non-native speakers, the types and frequencies of these mistakes are not random. Certain parts of speech, for example, have been shown to be especially problematic for Japanese learners of English [1]. Modelling these errors can potentially enhance the performance of computer-assisted language learning systems.This paper presents an automatic method to estimate an error model from a non-native English corpus, focusing on articles and prepositions. A fine-grained analysis is achieved by conditioning the errors on appropriate words in the context.

Correcting Different Types of Errors in Texts

“…[25] trains a maximum entropy model using lexical and POS features to recognize a variety of errors. Their evaluation data partially overlaps with that of [24] and our paper.…”

“…The work that is closely related to ours is that of Lee's [24], a supervised method built on the basic approach of template-matching on parse trees. To improve recall, the author uses the observed tree patterns for a set of verb form usages, and to improve precision, he utilizes n-grams as filters.…”

“…We also evaluate the proposed method using the NICT JLE corpus [22], to directly compare with [24]. The JLE corpus has 15,637 sentences with annotated grammatical errors and their corrections.…”

Author’s Native Language Identification from Web-Based Texts

“…Cyber users distribute messages mainly in English over cyberspace. Non-native English authors write in a systematic manner, and corpus of writings often depends on the first language of the writer [8], [9].…”

“…In our research, we included characterbased lexical features used in [8], vocabulary richness features in [11], and word-length frequency features used in [13]. In total, we adopted 64 lexical features to discriminating authors with different native languages in our texts shown in Table 1.…”