http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Research of Sentiment Classification for Tibetan Texts by Supervised Learning
Lirong Qiu,Zhen Zhang 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.9
Increasing number of subjective text appears on the internet which contains a lot of information. In this paper, we study how to apply supervised learning techniques to solve sentiment classification problems. Using the Tibetan news as data, we find that standard supervised learning techniques definitively outperform human-produced baselines. Moreover, we find that selecting the words with words with polarity as feature, the special syntactic structure such as exclamation sentence pattern, etc. as feature can improve the performance of sentiment classification. Conclusively, the research of sentiment analysis is a more challenging problem.
Syntactic Parsing Tree in Tibetan Language based on Context Free Grammars
Lirong Qiu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.11
Serving as a basic and key research of Tibetan information processing, Tibetan syntax analysis plays an important role in promoting the research on Tibetan natural processing technology such as machine translation, Tibetan information retrieval and semantic analysis. The existing Tibetan syntactic analysis system shows poor performance in general fields. Based on unique characteristics of Tibetan, through analysis and study on Tibetan syntax, the efficiency of sentence processing system can be improved, thus speeding up the progress of Tibetan sentence processing. In this paper, we proposed a syntactic parsing method based on context free grammars using up-bottom parsing technology.
An Opinion Analysis Model for Implicit Aspect Expressions based on Semantic Ontology
Lirong Qiu 보안공학연구지원센터 2015 International Journal of Grid and Distributed Comp Vol.8 No.5
Analyzing user opinion and building features model of entities is very important for sentiment analysis and opinion mining, which is the fundamental work for social network analysis. Opinions of entity can be classified into two types: explicit aspect expressions and implicit aspect impressions, and implicit aspect expressions might have some relationships which can be denoted by domain specific knowledge, existing previous works have not addressed in much detail. This paper defines an opinion mining model for implicit aspect expression based on semantic ontology, and proposes semantic similarity estimation approaches of entity by the domain ontology.
Tibetan-Chinese Bilingual Sentences Alignment Method based on Multiple Features
Lirong Qiu 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.4
Sentence-level aligning bilingual parallel corpus is shown significant and indispensable status in machine translation, translation knowledge acquiring and bilingual lexicography research fields, which is the fundamental work for natural language processing. Given the great deal of work in sentence alignment and a variety of methods have developed for bilingual terminology extraction, those are unpractical for newly underway Tibetan information processing because those methods have to use a large number of manufactured sentences as training corpus while extracting inter-translatable word pairs. This paper proposes a multi-strategy Tibetan-Chinese sentence alignment method based on length of sentence, syntactic rules and bilingual dictionary. We test our approach on a bilingual corpus crawled from bilingual website and perform manual evaluation on bilingual sentences pairs extracted from Tibetan-Chinese corpora.
A Graph-based Algorithm to Build Knowledge Map for Minority Languages
Lirong Qiu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.2
Knowledge mapping will undoubtedly bring great convenience to application users for being behind the strong support of knowledge base. In this paper, we study how to discover the evolution of knowledge map in multi-languages. Our approach is uniquely designed to capture the rich topology of semantic items and to link the sub-graph to a global knowledge map. Instead of building a knowledge map start from scratch, we conceptually define semantic classes as a quantized unit of evolutionary link in sub-graph and discover new knowledge with multi-language dictionaries. Discovered new knowledge items are then connected to form an evolution knowledge map using a measure derived from the underlying semantic classes. We integrate these noisy items and entities into a unified probabilistic knowledge map using ideas from graph-based algorithm.
Network Characteristics Analysis of Microblog Public Opinion
Lirong Qiu,Jie Li,Zhen Hai Zhang,Yi Lei Wang 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.10
This paper uses public opinion propagation structure of Sina microblog as research object, it sets up simulation model of public opinion propagation structures based on complex network theory. Through the analysis of the degree distribution, clustering coefficient and community structure of the model, the validity of the model has been well confirmed. The paper also conducts research and analysis towards propagation quantity of the hot topic within 800 well-known spread microblog from 2013 to 2015, the paper establishes a community structure, through the simulation and demonstration of the community structure, it declares the community structure characteristic under the complex network environment.
The Motivation of Electronic Voting towards Game Theory
Lirong Qiu 보안공학연구지원센터 2015 International Journal of u- and e- Service, Scienc Vol.8 No.5
With rapid development of computer science and network technology, the technology of electronic voting is widely applied in various fields. There are lots of security requirements in electronic voting such as privacy, verifiability, fairness and robustness etc. Previous works mainly discuss how to guarantee these requirements by using cryptographic tools, such as encryption, commitment etc. There, most works assume that parties are honest who will follow the protocol or malicious who will arbitrarily break the security of the protocol. In fact parties in real life are neither honest nor malicious, but instead they may consider the benefits when they decide to participate in voting. This paper discusses the motivations of parties to participate into voting towards the view of game theory. More specifically, motivations are quantized as the notion of utilities just as those in game theory. Then we prove how to assign people to have motivations to vote by achieving Nash equilibrium.