Sentence-level grammatical error identification as sequence-to-sequence correction

DSpace/Manakin Repository

Sentence-level grammatical error identification as sequence-to-sequence correction

Citable link to this page

 

 
Title: Sentence-level grammatical error identification as sequence-to-sequence correction
Author: Schmaltz, Allen Richard; Kim, Yoon; Rush, Alexander Matthew; Shieber, Stuart Merrill ORCID  0000-0002-7733-8195

Note: Order does not necessarily reflect citation order of authors.

Citation: Schmaltz, Allen, Yoon Kim, Alexander M. Rush, Stuart M. Shieber. 2016. Sentence-level grammatical error identification as sequence-to-sequence correction. Proceedings of the Eleventh Workshop on Innovative Use of NLP for Building Educational Applications, NAACL HLT, San Diego, California, June 16, 2016.
Full Text & Related Files:
Abstract: We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016. The attention-based encoder-decoder models can be used for the generation of corrections, in addition to error identification, which is of interest for certain end-user applications. We show that a character-based encoder-decoder model is particularly effective, outperforming other results on the AESW Shared Task on its own, and showing gains over a word-based counterpart. Our final model— a combination of three character-based encoder-decoder models, one word-based encoder-decoder model, and a sentence-level CNN—is the highest performing system on the AESW 2016 binary prediction Shared Task.
Other Sources: https://arxiv.org/abs/1604.04677
http://nlp.seas.harvard.edu/papers/aesw2016.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAP
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:27266472
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters