Auxiliary Objectives for Neural Error Detection Models on ShortScience.org

aclanthology.info
sci-hub
scholar.google.com

Auxiliary Objectives for Neural Error Detection Models
Rei, Marek and Yannakoudakis, Helen
Association for Computational Linguistics BEA@EMNLP - 2017 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Marek Rei 6 years ago

Investigating a range of auxiliary objectives for training a sequence labeling system for error detection. Automatically generated dependency relations and POS tags perform surprisingly well as gold labels for multi-task learning. Learning different objectives at the same time works better than doing them in sequence or switching.

https://i.imgur.com/81PvMfj.png

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private