Text analytics New and Noteworthy -- May-June, 2009 -- covering text analytics software, market, conference, and other news and developments to help readers better understand advances in Knowledge Discovery in Text...
OASIS, the international open standards consortium, announced on March 19 approval of the Unstructured Information Management Architecture (UIMA) version 1.0 as an OASIS Standard. Visit the OASIS UIMA Technical Committee page for information.
Product Releases and Announcements
Provalis Research released version 3.2 of QDA Miner on March 30. The company characterizes QDA Miner as "an easy-to-use qualitative analysis software tool or coding, annotating, retrieving and analyzing small and large collections of documents."
The Univ of Sheffield released GATE 5.0 on May 29th, offering JAPE pattern-language improvements, GUI improvements, and new ontology-based gazetteer, inter-annotator agreement, and other plug-ins. GATE, the General Architecture for Text Engineering, provides an open-source information extraction framework with many extensions. Release details can be found in the changelog, and the software may be downloaded at http://www.gate.ac.uk/download/.
Attensity announced the latest version of its Voice of the Customer (VoC) and Market Voice applications, Attensity 5, on June 1. A part of Attensity Group's suite of business applications for unstructured data, Attensity 5 offers integrated Automated Response for Customer Experience Management (CEM).
Teragram, a division of SAS, launched Sentiment Analysis Manager (SAM), a social media analysis tool, slated for late-July availability.
Nstein has announced TME 5, a next-generation Text Mining Engine, with fall 2009 availability. The new release will offer enhanced content enrichment, faceted sentiment analysis, full W3C compliant, and a RESTful interface.
Reports and Publications
My study report, Text Analytics 2009: User Perspectives on Solutions and Providers, is out. It reports findings of a survey I recently conducted and also provides an introduction to text analytics that is targeted to BI, data mining, and data warehousing practitioners and business analysts. The report is free. Download it via http://altaplana.com/TA2009.
The April issue of the quarterly newsletter of the (UK) National Centre for Text Mining (NaCTeM) is now available. (http://www.nactem.ac.uk/newsletter/)
DEFT'09, fifth edition of the Defi Fouille de Texte evaluation campaign in text mining, will address this year multilingual opinion analysis. The challenge, now under way, will culminate in a one-day workshop, June 22, 2009, near Paris.
SIGIR 2009, the Association for Computing Machinery's Special Interest Group on Information Retrieval, will convene July 19-23, 2009 in Boston.
The 2009 annual meeting of the Association for Computational Linguistics (ACL) will be combined with the International Joint Conference on Natural Language Processing (IJCNLP), taking place August 2-7, 2009 in Singapore.
The European Summer School in Information Retrieval (ESSIR) is slated for August 31-September 4, 2009 at the University of Padua, Italy. Closing date for registration is June 30.
The ACM Eighteenth Conference on Information and Knowledge Management (CIKM 2009) will take place in Hong Kong, November 2-6, 2009. The conference is sponsored by ACM SIGIR and SIGWEB.