Detecting Common Discussion Topics Across Culture From News Reader Comments
16
Citation
28
Reference
10
Related Paper
Citation Trend
Abstract:
News reader comments found in many on-line news websites are typically massive in amount.We investigate the task of Cultural-common Topic Detection (CTD), which is aimed at discovering common discussion topics from news reader comments written in different languages.We propose a new probabilistic graphical model called MCTA which can cope with the language gap and capture the common semantics in different languages.We also develop a partially collapsed Gibbs sampler which effectively incorporates the term translation relationship into the detection of cultural-common topics for model parameter learning.Experimental results show improvements over the state-of-the-art model.Cite
Citations (7)
The current retrieval methods are essentially based on the string-matching approach lacking of semantic information and can’t understand the user's query intent and interest very well. These methods do regard as the personalization of the users. Semantic retrieval techniques are performed by interpreting the semantic of keywords. Using the text summarization allows a user to get a sense of the content of a full-text, or to know its information content, without reading all sentences within the full-text. In this paper, a semantic personalized information retrieval (IR) system is proposed, oriented to the exploitation of Semantic Web technology and WordNet ontology to support semantic IR capabilities in Web documents. In a proposed system, the Web documents are represented in concept vector model using WordNet. Personalization is used in a proposed system by building user model (UM). Text summarization in a proposed system is based on extracting the most relevant sentences from the original document to form a summary using WordNet. The examination of the proposed system is performed by using three experiments that are based on relevance based evaluation. The results of the experiment shows that the proposed system, which is based on Semantic Web technology, can improve the accuracy and effectiveness for retrieving relevant Web documents.
Semantic Search
Relevance
Cite
Citations (14)
XML Schema (W3C)
Cite
Citations (14)
The expansion of structured information in different applications introduces a new ambiguity in multimedia retrieval in semi-structured documents. We investigate in this paper the combination of textual and structural context for multimedia retrieval in XML document thus we present a indexing model which combines textual and structural information. We propose a geometric method who use implicitly of textual and structural context of XML elements and we are particularly interested by improve the effectiveness of various structural factors for multimedia retrieval. Using a geometric metric, we can represent structural information in XML document with a vector for each element. Given a textual query, our model lets us combine scores obtained from each sources of evidence and return a list of relevant retrieved multimedia element. Experimental evaluation is carried out using the INEX Ad Hoc Task 2007 and the Image CLEF Wikipedia Retrieval Task 2010. The results show that combination of scores of textual modality and structural modality significantly improves compared results of using a single modality.
Modality (human–computer interaction)
Cite
Citations (0)
Content-based Semantic Web retrieval only considers the content itself,without taking into account the different users,and it can not accurately reflect user needs.Aiming at the problem,this paper proposes a framework for adaptive semantic Web retrieval.For Chinese documents on the Web,it gives a kind of ontology learning method with HowNet,builds user information database by extracting the user objective,explicit and implicit information,designs the initial query ontology and personalized query ontology construction algorithm,and ultimately achieves the user's adaptive retrieval.Result shows the method has higher retrieval efficiency.
Cite
Citations (0)
The paper introduces a method of multi-information similarity,based on the analysis of the Chinese Question-Answering System.And then the upcoming module of answer extraction could use the result set of candidacy from information retrieval to satisfy user's needs by rank of result set.The experiment shows that this method improves accuracy in retrieval of Web pages.
Similarity (geometry)
Rank (graph theory)
Cite
Citations (0)
Because of explosive growth of resources in the internet, the information retrieval technology has become particularly important. However the current retrieval methods are essentially based on the full text matching of keywords approach lacking of semantic information and can’t understand the user's query intent very well. These methods return a large number of irrelevant information, and are unable to meet the user's request. Systems have been established so far failed to overcome fully the limitations of search based on keywords. Such systems are built from variations of classic models that represent information by keywords. Using Semantic Web is a way to increase the precision of information retrieval systems. In this paper, we propose the semantic information retrieval approach to extract the information from the web documents in certain domain (jaundice diseases) by collecting the domain relevant documents using focused crawler based on domain ontology, and using similar semantic content that is matched with a given user’s query. Semantic retrieval approach aims to discover semantically similar terms in documents and query terms using WordNet.
Semantic Search
Web crawler
Cite
Citations (25)
The rapid growth and diversities of Web information bring a lot of difficulties to efficient information retrieval.The current information retrieval tools just offer-based searching,but ignore the semantic content of the keyword itself.The authors' library information retrieval system takes advantage of ontology,which expands the requirements of users to a semantic word set,and provides a document analyzer to filter the Web pages returned by the search agent according to a certain algorithm.Consequently it presents the most relavant documents to the users.
Semantic Search
Cite
Citations (1)
Problem statement: Search queries are short and ambiguous and are insufficient for specifying precise user needs. To overcome this problem, some search engines suggest terms that are semantically related to the submitted queries, so that users can choose from the suggestions based on their information needs. Approach: In this study, we introduce an effective approach that captures the user’s specific context by using the WordNet based semantic relatedness measure and the measures of joint keyword occurrences in the web page. Results: The context of the user query is identified and formulated. The user query is enriched to get more relevant web pages that the user needs. Conclusion: Experimental results show that our approach has better precision and recall than the existing methods.
Semantic Search
Information needs
Cite
Citations (5)
Aiming at the problem of traditional information retrieval based on key words, a domain ontology-based semantic information retrieval model is proposed.On the basis of establishing the relationship between the ontology concept and the content of document, pre-processes the user's query, calculates the similarity using domain ontology, and shows the sorted relative documents corresponding to the query.The built Web-based intelligent retrieval prototype validates the effectiveness of the model preliminarily.
Ontology Inference Layer
Cite
Citations (1)