Towards a unified search: Improving PubMed retrieval with full text

Journal of Biomedical Informatics(2022)

引用 2|浏览18
暂无评分
摘要
•Unifying PubMed and PubMed Central retrieval by combining full texts and abstracts.•Full text sections are of different value and are not directly comparable in biomedical search.•Random ranking achieves 0.579 MAP score on our PubMed Log click dataset.•BM25 ranking on PubMed abstracts improves the MAP by 10.6%•Including full text we improve to 11.36% over random, or 7% relative improvement.
更多
查看译文
关键词
Full text search,Information retrieval,PubMed search engine,Combining abstract with full text,Search relevance gold standard
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络