Adapting Sequence Models for Sentence Correction

EMNLP, pp. 2807-2813, 2017.

Cited by: 47|Bibtex|Views111|DOI:https://doi.org/10.18653/v1/d17-1298
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments