Currently there are a multitude of companies offering Content Analytics and Social Internet Mining services for the purposes of Opinion Mining and Sentiment Analysis. Truly effective Sentiment Analysis is a complex NLP task in monolingual contexts alone. In multilingual contexts the complexity increase many-fold and also presents the challenge of comparison of opinion across languages and cultures. Named Entity Recognition and Classification is also key element to this challenge. As with is often the case in many innovative sectors and industries, a high percentage of SMEs are active offering niche solutions to specific segments of the market and/or domains.
Acquiring or developing the base qualifying technologies require to enter this market is and expensive undertaking that redirects limited the resources of SMEs away from offering products and services that the market demands. The OpeNER project has as the goal of reuse and repurposing of exiting language resources and data sets to provide a set of underlying technologies to the broader community. OpeNER will focus on the provision of a supplementary sentiment lexicon with culturally normalised and graduated values. NERC will also be tackled leveraging Linked Data with the aim of bringing multilingual NERC up to par with state of the art in dominant languages.
The scope of OpeNER will be restricted to Spanish, English, French, German, Dutch and Italian. The general research of the project will be oriented toward a generic application domain, and later, refined and validated in the Tourism domain. This will be achieved in conjunction with and End User Advisory Board composed of European Tourism Promotion Agencies, an online Tourism Portal and other interested parties.
Furthermore, OpeNER will employ proven techniques from the Open Source community and develop an online development community thus ensuring the long term viability beyond the project timeframe. So that the benefits of the project are adopted and extensible to new domains and languages, OpeNER will strive to make the tools and techniques resulting from the project available under Open Source or Hybrid Licenses.
01/07/2012 - 30/06/2014