End-to-end neural opinion extraction with a transition-based model
作者：
Highlights：
• Sentence-level fine-grained opinion extraction to identify opinion expressions as well as their holders and targets.
• An end-to-end transition-based neural model for joint opinion entity recognition and relation classification.
• Beam search and global learning strategies to enhance the model performance.
• State-of-the-art performance on a benchmark dataset for neural opinion extraction.
摘要
•Sentence-level fine-grained opinion extraction to identify opinion expressions as well as their holders and targets.•An end-to-end transition-based neural model for joint opinion entity recognition and relation classification.•Beam search and global learning strategies to enhance the model performance.•State-of-the-art performance on a benchmark dataset for neural opinion extraction.
论文关键词：Opinion extraction,End-to-end,Transition-based system
论文评审过程：Received 6 March 2018, Revised 20 September 2018, Accepted 27 September 2018, Available online 4 October 2018, Version of Record 10 October 2018.
论文官网地址：https://doi.org/10.1016/j.is.2018.09.006
