Fusion of Domain Knowledge and Text Features for Query Expansion in Citation Recommendation.
KSEM (2)(2020)
摘要
Academic citation recommendation addresses the task of recommending citations for a scientific paper. Effective citation recommendation is greatly important for literature reviewing, literature-based discovery and a wide range of applications. In this paper, we propose a query expansion framework via fusing domain-specific knowledge and text features for academic citation recommendation. Starting from an original query, domain-specific and context-aware concepts are derived to expand the query to improve the performance of citation recommendation. From the perspective of enriching knowledge structure, domain-specific concepts are extracted from domain knowledge graphs such as ACM Computing Classification System and IEEE thesaurus. From the perspective of providing query scenarios, the query is extensively considered with context-aware concepts derived from text feature extraction. Then candidate concepts are filtered via distributed representations like BERT to expand the query. Experiments of citation recommendation for papers in public data sets show that our proposed model of query expansion improves the performance of academic citation recommendation.
更多查看译文
关键词
domain knowledge,query expansion,text features,recommendation
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要