On improving parsing with automatically acquired semantic classes
作者：
Highlights：
• 80% of parsing mistakes in appositions are due to a lack of semantic information.
• We automatically gather evidence on class-instance semantic compatibility from text.
• Classes are common nouns; instances are entities characterized by name and type.
• Our best model uses both sources of evidence with smoothed conditional probability.
• Experiments reach 91.4% accuracy, a 12.9% relative improvement over the baseline.
摘要
•80% of parsing mistakes in appositions are due to a lack of semantic information.•We automatically gather evidence on class-instance semantic compatibility from text.•Classes are common nouns; instances are entities characterized by name and type.•Our best model uses both sources of evidence with smoothed conditional probability.•Experiments reach 91.4% accuracy, a 12.9% relative improvement over the baseline.
论文关键词：Apposition parsing,Semantic class extraction,Unsupervised knowledge acquisition
论文评审过程：Received 2 December 2014, Revised 30 June 2015, Accepted 7 July 2015, Available online 23 July 2015, Version of Record 19 October 2015.
论文官网地址：https://doi.org/10.1016/j.knosys.2015.07.015
