Yuanyuan Liu

From WikiPapers
Jump to: navigation, search

Yuanyuan Liu is an author.

Publications

Only those publications related to wikis are shown here.
Title Keyword(s) Published in Language DateThis property is a special property in this wiki. Abstract R C
Cross-media topic mining on wikipedia Cross media
Sparsity
Topic modeling
Wikipedia
MM 2013 - Proceedings of the 2013 ACM Multimedia Conference English 2013 As a collaborative wiki-based encyclopedia, Wikipedia pro- vides a huge amount of articles of various categories. In addition to their text corpus, Wikipedia also contains plenty of images which makes the articles more intuitive for readers to understand. To better organize these visual and textual data, one promising area of research is to jointly model the embedding topics across multi-modal data (i.e, cross-media) from Wikipedia. In this work, we propose to learn the projection matrices that map the data from heterogeneous feature spaces into a unified latent topic space. Different from previous approaches, by imposing the ℓ1 regularizers to the projection matrices, only a small number of relevant visual/textual words are associated with each topic, which makes our model more interpretable and robust. Further- more, the correlations of Wikipedia data in different modalities are explicitly considered in our model. The effectiveness of the proposed topic extraction algorithm is verified by several experiments conducted on real Wikipedia datasets. Copyright 0 0
Determining relation semantics by mapping relation phrases to knowledge base Open Information Extraction
Relation Mapping
Wikipedia Infobox
Proceedings - 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 English 2013 0 0
A survey of RE-specific wikis for distributed requirements engineering Collaborative requirements activity
RE-specific wikis
Proceedings - 2012 8th International Conference on Semantics, Knowledge and Grids, SKG 2012 English 2012 Wiki, as one of the Web 2.0 technology, has received considerable interest due to its capability to support collaboratively online contents' creation in a flexible and simple manner. Lots of researchers and practitioners committed themselves to enhancing wiki's capability to support Requirements Engineering (RE). The main goal of this study is to discover all the available tools that use the wiki way or extend the wiki technology to support RE (called as RE-specific wikis), how these RE-specific wikis have been applied, and identify future research directions. We performed a survey through a thorough search for literature and tools that answer our research questions. After data synthesis, we found 12 available RE-specific wikis. And then, we drew out their features, evaluated their RE adaptability. Based on the above findings, we discussed future research directions on how to promote RE-specific wikis to support the collaborative requirements activities from representation, agreement and specification dimensions. 0 0
Feature selection in text categorization based on cloud model Cloud model
Feature selection
Text classification
Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication, ICUIMC'12 English 2012 In text domains, effect feature selection is to use a small amount of core information to delegate the text itself. This paper presents a new featured selection method with cloud model on text classification that was gathered from Wikipedia featured articles. The results reveal that the new featured selection metric based on cloud model outperformed the others. It can use a few featured to delegate text and achieve a good classification results. 0 0
A semantic geographical knowledge wiki system mashed up with Google Maps Geo-ontology
Google Maps
Mashup
Semantic wiki
Science China Technological Sciences English 2010 A wiki system is a typical Web 2.0 application that provides a bi-directional platform for users to collaborate and share much useful information online. Unfortunately, computers cannot well understand the wiki pages in plain text. The user-generated geographical content via wiki systems cannot be manipulated properly and efficiently unless the geographical semantics is explicitly represented. In this paper, a geographical semantic wiki system, Geo-Wiki, is introduced to solve this problem. Geo-Wiki is a semantic geographical knowledge-sharing web system based on geographical ontologies so that computers can parse and storage the multi-source geographical knowledge. Moreover, Geo-Wiki mashed up with map services enriches the representation and helps users to find spatial distribution patterns, and thus can serve geospatial decision-making by customizing the Google Maps APIs. 0 0
Building an online course based on semantic Wiki for hybrid learning Collaborative learning
Hybrid learning
Online course
Semantic wiki
Lecture Notes in Computer Science English 2010 By combining properties of Wikis with Semantic Web technologies, Semantic Wikis emerged with semantic enhancements. Based upon Semantic Wiki, this paper designs and develops an online course integrated with face-to-face instruction to support hybrid learning. Compared with general online courses, the course has three outstanding features. First, taken the learning object as the basic building blocks, the course organizes learning content in a structured, coherent and flexible way. Second, it motivates learners to be actively engaged in the collaborative learning process by allowing convenient course authoring, editing as well as adequate interaction. Third, it enables smart resource accessing with the provision of intelligent facilities, such as semantic search, relational navigation, course management, etc. 0 0
Tianwang at TREC-2006 QA track NIST Special Publication English 2006 This paper describes the architecture and implementation of Tianwang QA system2006, which works for the TREC QA Main task this year. The main improvement is: 1. add one well founded knowledge source from Web - Wikipedia, and employ some natural language processing technologies to extract high quality answers; 2. design and implement a new translation algorithm in query generation. The results show that fine organized knowledge source is effective in answering all three types of questions. And such query generation algorithm can be benefit from both Frequent Asked Questions on Web and past TREC QA data. 0 0