Using Hidden Markov Models for the accurate linguistic analysis of process model activity labels
作者:
Highlights:
• We propose a machine learning-based technique for activity label analysis.
• We conceptualize activity label analysis as a tagging task based on a Hidden Markov Model.
• Our technique overcomes the issues associated with the rule-based state of the art.
• Our technique no longer requires the manual specification of rules.
• A comparative evaluation with 15,000 labels demonstrates the superiority of our technique.
摘要
•We propose a machine learning-based technique for activity label analysis.•We conceptualize activity label analysis as a tagging task based on a Hidden Markov Model.•Our technique overcomes the issues associated with the rule-based state of the art.•Our technique no longer requires the manual specification of rules.•A comparative evaluation with 15,000 labels demonstrates the superiority of our technique.
论文关键词:Label analysis,Process model,Natural language,Hidden Markov models
论文评审过程:Received 27 December 2016, Revised 19 October 2018, Accepted 13 February 2019, Available online 17 February 2019, Version of Record 22 February 2019.
论文官网地址:https://doi.org/10.1016/j.is.2019.02.005