Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Danhao Zhu"'
Recently, neural network based methods have shown their power in learning more expressive features on the task of knowledge graph embedding (KGE). However, the performance of deep methods often falls behind the shallow ones on simple graphs. One poss
Externí odkaz:
http://arxiv.org/abs/2211.04620
Publikováno v:
Science China Information Sciences. 64
Several modern network embedding methods learn vector representations from sampled context nodes. The sampling strategies are often carefully designed and controlled by specific parameters that enable them to adapt to different networks. However, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c558fdaccb2e83ddcc9aa62de2c2c91c
https://doi.org/10.1007/s11432-019-2635-8
https://doi.org/10.1007/s11432-019-2635-8
Publikováno v:
Journal of informetrics
© 2019 Published by Elsevier Ltd. We propose a new method for computing the bibliographic coupling strength between two documents. This new method is based on the TF-IDF formula from the field of information retrieval. It is shown that this formula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::858798c1bd893eb731c2a94eefad3e1c
https://hdl.handle.net/10067/1603380151162165141
https://hdl.handle.net/10067/1603380151162165141
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783030161415
PAKDD (3)
PAKDD (3)
Through mapping network nodes into low-dimensional vectors, network embedding methods have shown promising results for many downstream tasks, such as link prediction and node classification. Recently, attributed network embedding obtained progress on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f3f9f434437025e8c23458fc91b9448
https://doi.org/10.1007/978-3-030-16142-2_13
https://doi.org/10.1007/978-3-030-16142-2_13
Publikováno v:
Journal of Web Semantics. 59:100498
Many scholar knowledge mining tasks depend on the representations of different scholar entities and their compositions, including author, publication venue and paper. However, the existing methods always tried to learn different kinds of scholar repr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2b54d98f9ad87b711437a67cce51dd8
https://doi.org/10.1016/j.websem.2019.02.001
https://doi.org/10.1016/j.websem.2019.02.001
Publikováno v:
Scientometrics. 97:435-442
Based on the network comprised of 111,444 keywords of library and information science that are extracted from Scopus, and taken into consideration the major properties of average distance and clustering coefficients, the present authors, with the kno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf53f8872921b5f0557ce80738e314a9
https://doi.org/10.1007/s11192-013-1019-3
https://doi.org/10.1007/s11192-013-1019-3
Publikováno v:
Scientometrics. 90:483-498
To better understand the distribution of words in all kinds of syntactic structures, the paper calculates the word distribution in syntactic structures of both English and Chinese. On the basis of the calculation, the article presents the definition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c31b2b06979ad5e0bbca38499ee90312
https://doi.org/10.1007/s11192-011-0546-z
https://doi.org/10.1007/s11192-011-0546-z
Publikováno v:
Scientometrics: an international journal for all quantitative aspects of the science of science and science policy
This investigation tries to determine if, for highly visible journals, namely Nature, Science and Cell, articles with a short editorial delay time generally, receive more citations than those with a long editorial delay. Based on data for the period
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::964979d82ca7e1a4575c168963689d96
https://hdl.handle.net/10067/1302530151162165141
https://hdl.handle.net/10067/1302530151162165141