Paper "Unsupervised Methods of Topical Text Segmentation for Polish" authored by Dominik Flejter and Karol Wieloch was accepted for workshop Balto-Slavonic Natural Language Processing (BSNLP 2007) organized in conjunction with ACL 2007.

Paper titled "Bottom-Up Discovery of Clusters of Maximal Ranges in HTML Trees for Search Engines Results Extraction" written by Dominik Flejter and Roman Hryniewiecki was presented today at the BIS 2007 conference at "Information Retrieval - Web Content" session. The PowerPoint presentation of the paper can be downloaded here.

Today Monika Starzecka, Adam Walczak and Dominik Flejter made a presentation for EDP company data administrators, analytics and software developers regarding possible applications of Integror solutions in the area of automotive Web and Deep Web data gathering and monitoring.

The list and order of presentations (altogether with full list of authors, papers and abstracts) that will be given during workshop on Social Aspects of the Web (SAW 2007) during BIS 2007 conference was posted to the BIS conference programme Web page. SAW 2007 presentations will be held on Friday, April 27.

Paper titled "Unsupervised Methods of Topical Text Segmentation for Polish" authored by Dominik Flejter, Karol Wieloch and Witold Abramowicz was sumbitted to workshop on Balto-Slavonic Natural Language Processing (BSNLP 2007) organized in conjuction with ACL 2007. The recently led research described in the paper applies experiences of Semantex project related to plain text documents segmentation to Polish language.

The abstract of the sumbitted paper reads: "This paper describes research on performance of existing unsupervised algorithms of text documents topical segmentation when applied to Polish plain text documents. For performance measurement five existing topical segmentation algorithms were selected, three different Polish test collections were created and seven approaches to text pre-processing were implemented. Based on quantitative results (Pk and WindowDiff metrics) use of specific algorithm was recommended and impact of pre-processing strategies was assessed. Thanks to use of standardized metrics and application of previously described methodology for test collection development, comparative results for Polish and English were also obtained."