【摘 要】
：
The task of automatic keyword extraction can be described as: given a document,the extractor is expected to automatically pick up several words that can most represent the content.Traditional methods
【机 构】
：
School of Electric Information and Electrical Engineering,Shanghai JiaoTong University
【出 处】
：
2014年国际计算机科学与软件工程学术会议
论文部分内容阅读
The task of automatic keyword extraction can be described as: given a document,the extractor is expected to automatically pick up several words that can most represent the content.Traditional methods in this sphere did not consider the semantic relationship between words.In this paper,we proposed a keyword extraction approach that took semantic association into account.We brought word embedding into this task based on the observation that articles authors always use different expressions which have the same meaning to make the content less tedious,particularly in Chinese.By using word embeddings we can easily calculate the distance between two words,which makes it convenient to find the semantic relationship between words.Experiment results shows that our approach is more reasonable and can grasp more semantic information in the document,comparing to traditional statistical methods.
其他文献
Cancer biomarker plays an important role in cancer diagnosis and treatment,but very few robust cancer molecular biomarkers are discovered in the last decades.This requires us to explore the causes to
For the applied limitation of the existing provably secure threshold decryption schemes on (t,n) structure,a provably secure threshold decryption scheme on access structure is proposed.The validity of
Combined with cotton twill market operators price index data,using Eviews software to model and empirically analyze cotton twill and single product price index on the basis of time series theory.The m
In order to improve the precision of low-aspect-ratio hydrofoils hydrodynamic performance evaluated by CFD numerical method at high incidence,simulations of a rectangle NACA0018 hydrofoil are carried
In recent years,the risk of the global natural disasters is expanding in space and increasing in intensity.It has become urgent priority to scientifically and reasonably construct the sharing platform
This paper proposes a recommended method of teaching resource basing on genetic algorithm collects the Chinese learning information of users,quantitates the information and codes for section,used as t
With the spatial data growing and being enriched,more and more users get spatial data through WMS services,which have reduced the efficiency of data access.It was estimated that 20% of data in WMS ser
Automatic search of impossible differentials for block ciphers is useful for impossible differential cryptanalysis.This paper introduces a tool to search impossible differentials.The idea of this tool
Digital Earth has the extraordinary ability to integrate spatial and temporal data with three dimensional,dynamic,can be immersive,intuitive and interactive features and is easy for people to understa
Cavitating flows can occur in a variety of practical applications.This paper focuses on the tip vortex cavitation of a marine propeller.Cavitating flows can be predicted using a wide range of methods.