期刊
TSINGHUA SCIENCE AND TECHNOLOGY
卷 23, 期 6, 页码 660-670出版社
TSINGHUA UNIV PRESS
DOI: 10.26599/TST.2018.9010011
关键词
knowledge base acceleration; cumulative citation recommendation; Mixture of Experts (ME); Latent Entity-Document Classes (LEDCs)
类别
资金
- National Key Research and Development Program of China [2016YFB1000902]
- National Natural Science Foundation of China [61472040, 61751217, 61866038]
- Natural Science Basic Research Plan in Shaanxi Province of China [2016JM6082]
- PhD start project of Yan'an University [YDBK2018-09]
Knowledge Bases (KBs) are valuable resources of human knowledge which contribute to many applications. However, since they are manually maintained, there is a big lag between their contents and the up-to-date information of entities. Considering a target entity in KBs, this paper investigates how Cumulative Citation Recommendation (CCR) can be used to effectively detect its worthy-citation documents in large volumes of stream data. Most global relevant models only consider semantic and temporal features of entity-document instances, which does not sufficiently exploit prior knowledge underlying entity-document instances. To tackle this problem, we present a Mixture of Experts (ME) model by introducing a latent layer to capture relationships between the entity-document instances and their latent class information. An extensive set of experiments was conducted on TREC-KBA-2013 dataset. The results show that the model can significantly achieve a better performance gain compared to state-of-the-art models in CCR.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据