Beta Release of LETOR3.0, a Benchmark Dataset for Learning to Rank

A report from Microsoft research asia:

LETOR is a package of benchmark data sets for research on LEarning TO Rank, released from Microsoft Research Asia.
This dataset contains standard features, relevance judgments, data partitioning, evaluation tools, and several baselines, for the OHSUMED data collection and the '.gov' data collection. Version 1.0 was released in March 2007. Version 2.0 was released in Jan. 2008. Since the release of LETOR2.0, we have received valuable feedbacks from many people, such as bug reports, feasibility studies of the tools, and so on. Based on the feedbacks, we launched the project of LETOR3.0 several months ago.
Now the beta version of LETOR30 is available at

http://research.microsoft.com/users/LETOR/.

What's new in LETOR3.0?
LETOR3.0 contains several significant updates:
1) Four new datasets were added: homepage finding 2003, homepage finding 2004, named page finding 2003 and named page finding 2004. Plus the three datasets (OHSUMED, topic distillation 2003 and topic distillation 3004) in LETOR2.0, there are seven datasets in LETOR3.0;
2) More reasonable document sampling strategy was adopted. As a result, there are some changes on the documents associated with each query in the three datasets in LETOR2.0.
3) More features for learning were added.
4) Meta data for each document was provided to enable research on features for learning to rank.
5) More baseline algorithms were provided (actually the baselines will be included in the final version of LETOR 3.0);
What to do for LETOR3.0?
1) We plan to release the final version of LETOR3.0 datasets in early Nov, 2008. If you find any problem with the current beta version, please kindly let us know. We will refine the datasets accordingly. Our goal is to make the datasets really reliable and useful for the community.
2) The baselines in LETOR3.0 will be released at mid of Dec, 2008. If you want your own algorithms to be included as official baselines in LETOR3.0, please contact us as soon as possible.
We would like to express our sincere thanks to you, for your suggestions and helps on LETOR in the past years. We look forward to receiving feedbacks from you.
Please feel free to send an email to letor@microsoft.com to contact Letor team.
Best regards,
Tao Qin, Tie-Yan Liu, Jun Xu and Hang LiMicrosoft Research Asia


With information ICSRG shares

Video Lectures in Computer Science

VideoLctures.net is a free web site where collect more than 5,000 useful videos from the most famous lecturers and scholars in prominent universities or conferences. Although, it covers almost all sciences, videos in computer science(about 1,500 videos) is the main part of this collection. You may also find the presentation files in this web site.

Videos in computer science are divided in more than 30 categories as follow:

Machine Learning, Text Mining and Web Mining, Information Retrieval, Semantic Web, Network Analysis, Complexity Science, Computer Vision and many more. To find more just surf http://videolectures.net/.

With information ICSRG shares

Research Methods Knowledge Base

The Research Methods Knowledge Base is a comprehensive web-based textbook that addresses all of the topics in a typical introductory research methods.

It covers the entire research process including: formulating research questions; sampling ; measurement ; research design ; data analysis; and, writing the research paper.

With information ICSRG shares

ICSRG Rules

1. ICSRG is a public media to improve Iranians’ ability to communicate as an international researcher. So, do not send your private messages.
2. ICSRG is a academic media. So, do not send any political,… messages.
3. Official language in this media is English. So, do not talk Finglish.
4. Members of this group should be Iranian.
5. All members can send messages about conferences to the group, but conferences should have following criteria:
   –Articles in the conference should publish in the indexed publication (Springer, IEEE, ACM, …) OR Conference should be in CS conference Ranking List.
   –The language should be English.
6. All members can send messages about journals to the group, but journals should have following criteria:
   –Journals should be indexed (ISI, INSPEC, SCOPUS, …)

With information ICSRG shares

How to find information about journals?

Open question 2:
Here we have some questions about journals:

1- How can we find the most prominent journals related to computer science?
2- What does ISI jounals mean?
3- How to access these information?

Kindly, leave you comment as answer.
With information ICSRG shares

How to write a research proposal?

Open question 3:
Here we have some questions about writing a proposal:

How to write a research proposal?
What are the most important parts of a proposal?
Are there any sample proposals to be used as a template?

Kindly, share your experience.
With information ICSRG shares

First Meeting Report

The first meeting of ICSRG was held on 18 September 2008. After introducing the goals, rules and current activities of ICSRG, members discussed about future trend of the group.
Brief outcomes of the meeting are:
1- Because of having some members in different countries, so ICSRG's activities should be extended by Internet utilities.

2- ICSRG is divided into six departments:
MM: MultiMedia (Image/speech processing)
AIML: Artificial Intelligence/ Machine Learning
DKMM: Database/Knowledge Management/ Data Mining/ Web Mining/Data Security
SEIS: Software Engineering/ Information System
NET: Network/ Distributed System/ Quantum Computing
HEHC: Hardware Engineering/High-performance Computing

3- We are going to publish news letters.

4- We will provide some useful information by adding Open Question in our weblog and Yahoo group.


You can access presentation file via http://groups.yahoo.com/group/ICSRG/files/General/

Your comments about our future trend are welcomed.
With information ICSRG shares