Learning to extract domain-specific relations from complex sentences
作者：
Highlights：
• We propose SemIE, Semantic-based Information Extraction and Mapping.
• Our approach identifies significant relations and maps them to a semantic structure.
• Our approach bootstraps training examples from a pair of structured documents.
• The results show our approach outperforms current state-of-the-art system.
• The results prove the effectiveness of our approach in handling complex sentences.
摘要
•We propose SemIE, Semantic-based Information Extraction and Mapping.•Our approach identifies significant relations and maps them to a semantic structure.•Our approach bootstraps training examples from a pair of structured documents.•The results show our approach outperforms current state-of-the-art system.•The results prove the effectiveness of our approach in handling complex sentences.
论文关键词：Open information extraction,Structure mapping,Bootstrapping training examples,Greedy mapping
论文评审过程：Received 28 December 2015, Revised 1 May 2016, Accepted 2 May 2016, Available online 3 May 2016, Version of Record 13 May 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.05.004
