Archive for Information Retrieval
July 3, 2008 at 4:59 am · Filed under Information Retrieval ·Tagged NLP, semantic search
Confirmed: Microsoft Acquires Powerset – ReadWriteWeb
The software giant has finally acquired Powerset. I hope the technology of Powerset will be expanded to span the entire web instead of just Wikipedia which is the case now. It will be interesting to see how effective that will be compared to keyword and page rank based robust technology of Google. It is important that giants like Microsoft and Google demonstrate semantic applications rather than conservatively sticking to simple keyword based technologies. However, I am not sure if natural language querying will be more effective and appealing than keyword search. I think it is much easier to do keyword queries than typing in full questions.
Permalink
November 4, 2007 at 9:49 am · Filed under annotation, Information Retrieval, My Projects, Ontology, semantic annotation, Semantic Blogging, semantic search
OntoBlog: Linking Ontology and Blogs
I presented this paper in the Semantic Authoring, Annotation and Knowledge Markup Workshop (SAAKM 2007) co-located with the 4th International Conference on Knowledge Capture (K-Cap 2007), Whistler, British Columbia, Canada. It was an interesting workshop followed up by enthusiastic discussions.
Online proceedings is available here. You can download my paper here and these are my slides.
Permalink
July 17, 2007 at 6:22 am · Filed under Information Retrieval, Semantic web, Tools, Web 2.0
Talis
Came across this new Semantic Web application platform. They say the platform comprises a powerful combination of Semantic Web, information retrieval, collective intelligence and behavioural mining technologies .
Permalink
April 3, 2007 at 10:02 am · Filed under Folksonomy, Information Retrieval, Ontology, Projects, Semantic Blogging
ICWSM || Full Paper || Using Ontologies to Strengthen Folksonomies and Enrich Information Retrieval in Weblogs: Theoretical background and corporate use-case
This work is similar to my thesis on semantic blogging. Tags are mapped to ontology in this work while blog entries are directly mapped to ontology in my work.
Abstract:
While free-tagging classification is widely used in social software implementations and especially in weblogs, it raises various issues regarding information retrieval. In this paper, we describe an approach that mixes folksonomies and semantic web technologies in order to solve some of these problems, and to enrich information retrieval capabilities among blog posts.
We first introduce the corporate context of the study and the issues we have faced that motivated our approach. Then, we argue how the use of domain ontologies combined with the SIOC vocabulary on the top of an existing folksonomy and weblogging platform offers a way to get rid of free-tagging classification flaws, and enhances information retrieval by suggesting related blog posts.
Aside of the theoretical background, this paper also focuses on implementation. We present experimental results of this approach through the example of add-ons to a corporate blogging platform and the associated semantic web search engine, that extensively uses RDF and other semantic web technologies to find appropriate information and suggest related posts.
Permalink