Zhao Lu - IEEE Xplore Author Profile

Showing 1-23 of 23 results

Filter Results

Show

Results

Recent years have shown rapid advancement in understanding consumers' behaviors and opinions through collecting and analyzing data from online social media platforms. While abundant research has been undertaken to detect users' opinions, few tools are available for understanding events where user opinions change drastically. In this paper, we propose a novel framework for discovering consumer opin...Show More
The lasting popularity of many social Q&A websites, such as Yahoo! Answers and ResearchGate, has become valuable knowledge repositories for people to search for answers to questions in various aspects in life. Finding the most relevant questions is often a non-trivial task, and a fine-grained classification system of questions will be an important aid. Existing work mainly focused on classifying q...Show More
With the growth of web documents, the ambiguity of personal name becomes more common and brings poor performance of web search. Identifying a correct personal entity from the a piece of or the whole document is still a very challenging problem, especially for Chinese websites. In this paper, we propose a novel Ontology-based approach for Personal Name Disambiguation (named "OnPerDis"). This approa...Show More
Relational similarity measurement as a popular research area in the field of natural language processing, is widely used in information retrieval, word sense disambiguation, machine translation and so on. The existing approaches are mostly based on extracting semantic features as feature matrixes from the large-scale corpus and using the corresponding method to process these feature matrixes to co...Show More
There are some specific relations between the entities of the nature. The same relationship exists between two pairs of entities, simply to say, what A is to B as C is to D. For two unfamiliar entities (A, B), We cannot say precisely the relationship between them. When given an instance C similar to A, we cannot say out the entity D corresponding to B. Latent relation search provides a new way of ...Show More
It is very common that various people share same name or a person has various names, which causes person name ambiguities. Existing methods group documents containing person names into various clusters and each cluster refers to an individual, while which target individual a person name occurring in a document refers to is still a challenged problem. In this paper, we firstly construct a person on...Show More
Chinese Transliterated Person Name (TP-Name) recognition is a special challenging task in Chinese unknown word recognition and Chinese word segmentation. Most of existing researches mainly focus on recognizing the names of Chinese person while seldom specialize in recognizing transliterated person names. In this paper, we proposed a hybrid method for TP-Name recognition based on both the context o...Show More
Existing evaluation methods either investigate whether ontologies are “fit for purpose”, or focus on evaluating consistencies of the data in regard to the axioms defined in the ontologies. In this paper, we focus on how to evaluate the consistency of ontology with respect to taxonomic relationships, and we suggest a new measure to evaluate the taxonomic consistency of an ontology. As the semantic ...Show More
There is a great deal of research on the structural and logical matching of ontologies, and there is also considerable work on matching data instances from heterogeneous schema or ontologies, however, little work exploits the fact that ontologies include both data and structure. In this paper, we aim to present a new ontology matching architecture that tightly integrates both semantic similarity m...Show More
The problem of measuring semantic similarity between word pairs has been considered as a fundamental operation in natural language processing, such as information retrieval, word sense disambiguation, etc. Nevertheless, developing a computational method capable of generating satisfactory results close to what humans would perceive is still a difficult task somewhat owed to the subjective nature of...Show More
As a scheduled World Expo in the grand tradition of international fairs and expositions, Shanghai World Expo (SWE) has recently gained much attention for its highly sophisticated online vision called "Online Expo Shanghai". In this context, researchers are working to provide intelligent mechanisms to SWE. To support intelligent SWE managements and services, SWE modeling is an essential requirement...Show More
The problem of measuring the semantic similarity between words has been considered a fundamental operation in the field of computational lexical semantics, but the accuracy of existing computational methods is not very close to what humans would perceive. This paper presents a new approach to measure the semantic similarity between words in the hierarchy of WordNet. Our approach considers not only...Show More
Two important challenges in the wide deployment of location-based services (LBSs) are privacy and confidentiality. Existing privacy-enhancing techniques rely on encryption to safeguard communication channels, and on pseudonyms to protect user identities, or rely on a well-established k-anonymity area without characters to compute exact answers for range and nearest neighbor search without revealin...Show More
In recent years, the travel time predictions have become a popular research topic. In this paper, we present a new algorithm of the travel time predictions based on the idea of using the shared traveler's positions to collect traffic conditions. Several experiments show that our algorithm has a broader applied area than existing algorithms and can provide real-time and the accurate predictions for...Show More
In this paper, we propose a new measure framework for evaluating taxonomy relationships in ontologies using lexical semantic relatedness. First, we suggest a new quantitative measure model for WordNet, the model can be used to compute the semantic relatedness of concepts in ontologies. Next, according to the relativities of concepts, we describe the way to estimate the classification consistency o...Show More
A new method to compute the similarity of two blog posts is proposed in this paper. This method mainly has two parts including keywords extraction and semantic similarity measurement. During keywords extraction part, the method utilizes particular post features to extract keywords from one blog post with the aim to improve the correlation rate. In order to compute the similarity of any two blog po...Show More
Email classification methods based on the content general use Vector Space Model. The model is constructed based on the frequency of every independent word appearing in Email content. Frequency based VSM does not take the context environment of the word into account, thus the feature vectors can not accurately represent Email content, which will result in the inaccurate of classification. This pap...Show More
Semantically-based watermarking scheme embeds the information by transforming semantic structure of the sentence. In this paper we propose an optimized semantic watermarking algorithm which introduces TMR string reranking mechanism before watermark embedding. The optimized algorithm has the feature of resisting sentence reordering attack to a certain extent. To evaluate the effectiveness of our al...Show More
The openness of Internet leads to security problems of network, among which content security is an important problem. In order to solve the problem effectively, a security scheme of information content which based on content security ontology (CSO) is presented. CSO is extracted from a security kernel (SK) which is a lexicon of information security knowledge drawing out from general thesaurus and ...Show More
This paper focuses on personalized information retrieval which is a research focus in Web information service, and itpsilas the key technology of enhance retrieval quality. As a user concept map composed of some concepts that extended from user queries based on user interests description, it's the embodiment of user's true intention. Each concept weight in the concept map is defined as a probabili...Show More
Recently, researches on the workflow modeling and verification mostly focused on the structure of workflow process pay less attention to descript data, resources, and structure of a workflow process simultaneously. This paper proposes a novel semantic modeling and verification approach of a workflow which can describe these three parts at the same time based on CSP. The effective of the approach i...Show More
From the scenario of remote learning, we put forward that the floor control policy must consider the spatial fairness between different teaching points. Firstly, a floor tree was put forward to record the spatial distribution of historical floor assignment and then floor index was constructed to judge the spatial priority of learners' floor requests; Secondly, a spatial fairness based floor sortin...Show More
For security and share of Internet IP addresses, NAT (network address translation) firewalls are widely used to isolate the private networks from Internet in some enterprises/organizations. Unfortunately, NATs block the data transmitted directly between two clients under different private networks in many P2P (peer to peer) applications. A protocol, STUN, has been proposed by IETF to solve the pro...Show More