A novel reasoning mechanism for multi-label text classification
作者:
Highlights:
• A novel reasoning-based algorithm named ML-Reasoner for multi-label text classification is proposed.
• Each instance of reasoning in this method takes the previously predicted likelihoods for all labels as additional input.
• Not only is the method able to avoid the dependency of label orders completely, but it also achieves competitive performance when handling with multi-label datasets.
• Applying the reasoning mechanism to three strong neural-based base models can achieve significant performance improvements on all two data sets.
• The method achieves state-of-the-art results on two challenging multi-label datasets.
摘要
•A novel reasoning-based algorithm named ML-Reasoner for multi-label text classification is proposed.•Each instance of reasoning in this method takes the previously predicted likelihoods for all labels as additional input.•Not only is the method able to avoid the dependency of label orders completely, but it also achieves competitive performance when handling with multi-label datasets.•Applying the reasoning mechanism to three strong neural-based base models can achieve significant performance improvements on all two data sets.•The method achieves state-of-the-art results on two challenging multi-label datasets.
论文关键词:Multi-label learning,Text classification,Label embedding,Iterative reasoning mechanism,00-01,99-00
论文评审过程:Received 17 January 2020, Revised 15 July 2020, Accepted 14 November 2020, Available online 29 November 2020, Version of Record 29 November 2020.
论文官网地址:https://doi.org/10.1016/j.ipm.2020.102441