Journal of Computer Science and Technology - Entity linking (EL) is the task of determining the identity of textual entity mentions given a predefined knowledge base (KB). Plenty of existing... 相似文献
Heterogeneous information networks, which consist of multi-typed vertices representing objects and multi-typed edges representing relations between objects, are ubiquitous in the real world. In this paper, we study the problem of entity matching for heterogeneous information networks based on distributed network embedding and multi-layer perceptron with a highway network, and we propose a new method named DEM short for Deep Entity Matching. In contrast to the traditional entity matching methods, DEM utilizes the multi-layer perceptron with a highway network to explore the hidden relations to improve the performance of matching. Importantly, we incorporate DEM with the network embedding methodology, enabling highly efficient computing in a vectorized manner. DEM’s generic modeling of both the network structure and the entity attributes enables it to model various heterogeneous information networks flexibly. To illustrate its functionality, we apply the DEM algorithm to two real-world entity matching applications: user linkage under the social network analysis scenario that predicts the same or matched users in different social platforms and record linkage that predicts the same or matched records in different citation networks. Extensive experiments on real-world datasets demonstrate DEM’s effectiveness and rationality.
A new skeletal mechanism of n-butane is developed for describing its ignition and combustion characteristics applicable over a wide range of conditions: initial temperature 690–1430 K, pressure 1–30 atm, and equivalence ratio 0.5–2.0. Starting with a detailed chemical reaction kinetic model of 230 species and 1328 reactions (Healy et al., Combust. Flame, 2010), the directed relation graph method is applied as the first step to derive a semi-detailed mechanism with 134 species. Then, the reaction path analysis in conjunction with temperature sensitivity analysis is used to remove the redundant species and reaction paths simultaneously under the condition of low-temperature and moderate-to-high temperatures, respectively. Finally, a skeletal n-butane mechanism consisting of 86 species and 373 reactions can be obtained. Mechanism validation indicates that the new developed skeletal mechanism is in good agreement with the detailed mechanism in predicting the global ignition and combustion characteristics. The new skeletal mechanism is further validated using extensive available literature data including rapid pressure machine ignition delay time, shock-tube ignition delay time, laminar flame speed, and jet-stirred reaction oxidation, covering a large range of temperatures, pressures, and equivalence ratios. The comparison results demonstrate that a satisfactory agreement between predictions and experimental measurements is achieved. 相似文献