ReliAble dependency arc recognition

作者：

Highlights：

• We propose a novel natural language processing task, ReliAble Dependency Arc Recognition (RADAR).

• We model RADAR as a binary classification problem with imbalanced data.

• We design three sorts of features to express reliability of arcs and evaluated the contributions of these features.

• A logistic regression classifier is trained to recognize reliable dependency arcs.

• The classification method can outperform a probabilistic baseline method.

摘要

•We propose a novel natural language processing task, ReliAble Dependency Arc Recognition (RADAR).•We model RADAR as a binary classification problem with imbalanced data.•We design three sorts of features to express reliability of arcs and evaluated the contributions of these features.•A logistic regression classifier is trained to recognize reliable dependency arcs.•The classification method can outperform a probabilistic baseline method.

论文关键词：Natural language processing,Syntactic parsing,Dependency parsing,RADAR,Binary classification

论文评审过程：Available online 13 September 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.08.070