RESTful semantic tag extraction service
SiLCC is a cloud based service for parsing text and extracting relevant keywords. To use it, you must first apply for an API key. Input the API key into your application and then push content to our server. As we receive your content, we parse it, extract relevant 'tags', then send it back to your app. From there user interaction with those tags (editing or removal) helps to improve our algorithms.
SiLLC also features robust glossaries for Twitter pico-formats and SMS txtSpeak. It specializes in the semantic tagging of content that's 280 characters and less.
get api key · documentation · live demo · plugins
Why SiLCC?
SiLCC is important because the act of tagging content is tedious and humans will often fail to do it. By using this RESTful natural language parsing service, you app can examine content and extract the keywords that are most relevant.
From the SMS "Major Earthquake in Chile", the important keywords are going to be 'earthquake' and 'chile'. These keywords can be used to find other content referencing the terms 'earthquake' or 'chile'. In essence that is predictive tagging, where algorithms try to extract meaning to help improve sorting. Users can then vote on these tags to help our algorithms improve. This then allows your app to determine the relationship between content, regardless of the source.
Installation
There are three types of links provided below. 'Get API Key' is the first step to using SiLCC. 'Documentation' is for programmers interested in using the SiLCC API to develop their applications. 'demo' offers examples of use. 'plug-ins' is an area for downloading easy install SiLCC plugins for a number of platforms like Ushahidi, Swift River, Wordpress, Drupal and more. **coming soon**
get api key · documentation · plug-ins
Advanced Taxonomy
SiLCC's parsing algorithms extend beyond normal text. Services like Twitter have robust pico-format ontology that SiLCC attempts to understand. This allows for the service to dig into hashtags and other picoformats via the twitter API to get even more robust information. *glossaries coming soon*
read more