Here is detailed information about the fifth cycle of ROMIP:
Results and ROMIP'2007 participants reports are available in the Publications section.
- 3 April 2007
Official start of ROMIP'2007. The call for participation
- 7 April 2007
Announced about the 1st Russian Summer School in Information Retrieval
took place in Ekaterinburg, Russia in September 2007 and attracted more than
- 1 May 2007
List of ROMIP'2007 participants was
- 14 June 2007
Descriptions of ad hoc search and classification
tracks including tasks and results format were published.
- 25 June 2007
Descriptions of query-biased summarization, news
clustering and similar documents search tracks including tasks and results
format were published.
- 20 September 2007
The evaluation results for the track of ad hoc search in the collection of legal
documents are sent to the participants.
- 25 September 2007
The evaluation results for the ad hoc search in the collection of
Web pages and mixed collection tracks are sent to the participants.
- 1 October 2007
The evaluation results for the tracks of Web site and Web pages
classification are sent to the participants.
- 10 October 2007
Announced that the publication of ROMIP'2007 proceedings is prolonged
because of delays in the evaluation process.
- 18 October 2007
ROMIP'2007 workshop took place in Pereslavl on October 18, 2007.
It was collocated with RCDL'2007
and Yandex Web research grant initiative ("Internet Math 2007").
Agenda included six presentation and round table
discussion about ROMIP's future.
- 20 October 2007
Slides from ROMIP workshop in Pereslavl are available.
- Mikhail Ageev (Moscow State University)
- Pavel Braslavski (Yandex, Moscow)
- Maxim Gubin (Ask.com)
- Boris Dobrov (UIS RUSSIA, Moscow)
- Igor Kuralenok (Yandex, St. Petersburg)
- Igor Nekrestyanov (Sun Microsystems, St. Petersburg)
- Vladimir Pleshko (Garant-Park-Internet, Moscow)
- Ilya Segalovich (Yandex, Moscow)
- Vlad Shabanov (Rambler, Moscow)
"Galaktika-Zoom" is a text mining solution working with unstructured
information. The system includes tools for text search and analisys based on
linguistic, mathematical and statistical methods.
This work suggests the technology of the news bulletin building, based on
the automatic analysis of the news reports. This technology includes methods
of the automatic picking out, ranking and abstracting of the news reports.
Splitting of the text messages into the fragments permits to improve the
quality of the cluster analysis and abstracting.
RCO team is focused on research in area of computer linguistics and
development of text analysis solutions for full-text databases,
data-warehouses and BI systems. In the workshop we are planning to drive
several experiments on text categorization and news clustering tasks.
Research project aimed for creating and evaluating recurrent
thematic Web search system.
Web search engine KM.ru
KM.ru at RIRES-2007 aims to evaluate the effectiveness of a new web search
engine realizing the functions of a classical information retrieval system. The
fundamentals of the system are approved traditional algorithms combined with proper