The mission of iZENEsoft is to research, innovate, and develop services and products in the areas of data mining, machine learning, and search technologies to help people make informed decisions.

About iZENEsoft

iZENEsoft is a software research & development company located in Shanghai, wholly owned by WISEnut, Inc. iZENEsoft is dedicated to provide software solutions to help people make informed decisions through the state-of-the-art technology researches in the areas of data mining, machine learning, and search engine technologies. iZENEsoft is especially committed to providing long-term reusable and scalable component-based software solutions. Since founded in early 2008, iZENEsoft has been developing a variety of software products in helping people search, analyze, and organize data they manage in their organizations for any purpose. The software products will be launched in the Chinese market in early 2010.

WISEnut, located in Seoul, Republic of Korea, is a market leader in enterprise search engine industry and a major player in keyword search advertisement industry in Korea. WISEnut has over 1000 clients for its products and services and has been rapidly growing since founded in 2000. It was selected by Deloitte Technology as one of the 500 fastest growing companies in Asia Pacific in 2005.

What's New

Syndicate content

A proximity language model for information retrieval

Author: 
Jinglei Zhao, Yeogirl Yun
Published in: 

The 32nd international ACM SIGIR conference on Research and development in information retrieval 2009

Abstract: The proximity of query terms in a document is a very important information to enable ranking models go beyond the "bag of word" assumption in information retrieval. This paper studies the integration of term proximity information into the unigram language modeling. A new proximity language model (PLM) is proposed which views query terms' proximity centrality as the Dirichlet hyper-parameter that weights the parameters of the unigram document language model.

WISE IF

Posted Wed, 2009-12-02 13:47

Background

Currently the users use crawlers to crawl web pages from the Internet and extractors to extract information they need. But no existing robots can the two together since the web pages are of various formats. While the need of a robot, who can crawl the web pages user need and extract accurate information from the pages crawled, is increasing.

Overview

IF is such a system to meet the requirement. Through rule definition, IF can accurately know what kind of page to crawl and what information to extract. It's a powerful tool to help the user to find and collect accurate information.

i-Classifier

Posted Wed, 2009-12-02 11:53

Background

The number of digital documents available in corporate intranets, digital libraries, commercial data bases or the Web as a whole is vastly growing in size. The sheer volume makes it often prohibitively expensive, if not impossible, to rely on librarians or other domain experts to efficiently annotate and categorize content. Consequently, automated document categorization is an important component in many information systems.

Overview

i-Classifier is the best tool to automatically classify large scale documents into appropriate categories and gives the user higher level logical view. You can get a quite effective and convenient experience by using i-Classifier, for example, separate taxonomies can be created for the sales, marketing, human resources, and engineering departments, and documents can be classified automatically to the hierarchy of these taxonomies. This structure information adds a valuable dimension to the content discovery process.

more
Syndicate content