Detecting article errors in English learner essays with recurrent neural networks

DSpace Repository

Show simple item record

dc.contributor.advisor Xue, Nianwen
dc.contributor.author Garimella, Manaswini
dc.date.accessioned 2016-08-31T15:17:50Z
dc.date.available 2016-08-31T15:17:50Z
dc.date.issued 2016
dc.identifier.uri http://hdl.handle.net/10192/32890
dc.description.abstract Article and determiner errors are common in the writing of English language learners, but automated systems of detecting and correcting them can be challenging to build as the context in which an article is found can be ambiguous. Here, I investigate the use of recurrent neural networks to detect and correct such errors separately, treating it as a sequence labeling task. The NUS Corpus of Learner English is used for training and evaluation. A maximum precision of 76%, recall of 41%, and F0.5 score of 46.5% were achieved in the error detection task using a bidirectional LSTM. A maximum precision of 51%, recall of 34%, and F0.5 score of 47% were achieved in the error correction task using a bidirectional LSTM, which is competitive with previous results on this corpus and recent results using other neural network models. Furthermore, the technique used relies only on lexical items, with no additional features necessary. These results, in conjunction with clear venues for improvement, show that the method is a promising one for the task.
dc.description.sponsorship Brandeis University, Graduate School of Arts and Sciences
dc.format.mimetype application/pdf
dc.language English
dc.language.iso eng
dc.publisher Brandeis University
dc.relation.ispartofseries Brandeis University Theses and Dissertations
dc.rights Copyright by Manaswini Garimella 2016
dc.subject computational linguistics
dc.subject English language learning
dc.subject grammatical error correction
dc.subject recurrent neural networks
dc.title Detecting article errors in English learner essays with recurrent neural networks
dc.type Thesis
dc.contributor.department Graduate Program in Computational Linguistics
dc.degree.name MA
dc.degree.level Masters
dc.degree.discipline Computational Linguistics
dc.degree.grantor Brandeis University, Graduate School of Arts and Sciences


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search BIR


Browse

My Account