Posts Tagged ‘text’

Phrase Detectives is a “Game with a Purpose”, meaning that the data we collect will be used to help improve computer systems. The data will be used to train anaphora resolution systems that can be used to improve text summarisation and search engine indexing, which will ultimately lead to a better Web experience for you.

Players of Phrase Detectives have submitted nearly 1 million relationships between phrases, with over 200 documents completed – a total of 60,000 words. From this point, a panel of expert linguists analysed a selection of documents and in most cases the top answer from Phrase Detectives (i.e. the answer that most detectives agreed with) was correct. This is great news as it shows that, by collaborating in a group, players make the right decisions in the end.

This month’s competition is a daily prize draw where you could win an Amazon voucher just by playing the game. The more you play each day the greater chance you have of winning. Winners will be updated on the homepage and contacted via email. More details are on the website…

On the other hand, there have also been updates to the game. You can now see all the completed documents – maybe you were the one who made the final decision on a document? There are also more hints and tips about playing the game. And remember you can score points for signing up new players, just email the link on your player homepage to your friends.

More info at: http://anawiki.essex.ac.uk/phrasedetectives/

The Aberystwyth University from the UK has just released SAPIENT in the context of the ART project.

SAPIENT stands for “Semantic Annotation of Papers: Interface & ENrichment Tool”. It is an annotation interface implemented as a web application, to help users annotate scientific papers in XML, sentence by sentence, with a set of concepts called General Scientific Concepts (GSCs, see http://ie-repository.jisc.ac.uk/88/). GSCs constitute the set of concepts essential for describing a scientific investigation. However, SAPIENT can also be used in conjunction with other annotation schemas to annotate papers in XML sentence by sentence.SAPIENT also incorporates Oscar3 functionality, allowing the automatic annotation of chemical named entities.

SAPIENT includes the so called SAPIENT Sentence Splitter (SSSplit). SSSplit is an XML-aware sentence splitter which preserves XML markup and identifies sentences through the addition of in-line markup. The reason for developing our own sentence splitter was that sentence splitters widely available could not handle XML properly. The XML markup contains useful information about the document structure and formatting in the form of inline tags, which is important for determining the logical structure of the paper.

SSSplit has been written in the platform-independent Java language (version 1.6), based on and extending open source Perl code for handling plain text. In order to make our sentence splitter XML aware, we translated the Perl regular expression rules into Java and modifed them to make them compatible with the SciXML schema.

Via: http://zillman.blogspot.com/2009/11/sapient-semantic-annotation-of-papers.html

You can get it at: http://altaplana.com/TA2009

SCRIBO – Semi-automatic and Collaborative Retrieval of Information Based on Ontologies – aims at algorithms and collaborative free software for the automatic extraction of knowledge from texts and images, and for the semi-automatic annotation of digital documents. SCRIBO has a total budget of 4.3Me and is partially funded by the French administration. It brings 9 participants together: AFP, CEA LIST, INRIA, LRDE (Epita), Mandriva, Nuxeo, Proxem, Tagmatica and XWiki.

The Scribo project will take part in the Open World Forum, the leading global summit bringing together decision-makers from across the world to discuss the technological, financial and social impact of open technologies. On October 1,2 2009, the Open World Forum 2009 will bring together all the key players in the open source ecosystem to cross-fertilize initiatives for innovation and economic growth.