Frequently Asked Questions
What is Calais?
The Calais initiative seeks to help make all the worlds content more accessible, interoperable and valuable via the automated generation of rich semantic metadata, the incorporation of user defined metadata, the transportation of those metadata resources throughout the content ecosystem and the extension of it’s capabilities by user-contributed components.
The Calais initiative has three major components:
- The Calais Web Service is the core. The Web service provides for the automated generation of rich semantic metadata in RDF format.
- A series of sample applications to demonstrate how the web service can be utilized and serve as a starting point for other’s development activities.
- Active support for developers that want to incorporate Calais capabilities in their applications and web sites.
The Calais initiative is sponsored by Reuters and built on ClearForest technology.
What Does the Calais Web Service Do?
From a user perspective it’s pretty simple: You hand the web service unstructured text (like news articles, blog postings, your term paper, etc) and it returns semantic metadata in RDF format. What’s happening in the background is a little more complicated.
Using natural language processing and machine learning techniques, the Calais web service looks inside your text and locates the entities (people, places, products, etc), facts (John Doe works for Acme Corp) and events (Jane Doe was appointed as a Board member of Acme Corp) in the text. Calais then processes the entities, facts and events extracted from the text and returns them to the caller in RDF format.
Please also drop by the Calais roadmap to see where Calais is headed. Significant development activities include the ability for downstream content consumers to retrieve previously generated metadata using a Calais-provided GUID (link to http://en.wikipedia.org/wiki/Guid), additional input languages and user defined processing extensions.
Entities? Facts? Events?
Comprehensive documentation on the many types of metadata that Calais can provide is located in the API Response section of the documentation. But remember – this is just the start. Visit the roadmap to see what’s coming in the near future.
Who Can Use It?
Just about anyone. The Calais Web Service is available for use for both commercial and non-commercial purposes by individual developers, software companies, researchers, web sites and others. There are a few specific restrictions on what you can use it for mentioned in the license agreement – but we’ve tried to keep it as open as possible.
What’s Coming Next?
See the roadmap. We’ll be keeping this up to date as new development initiatives kick off.
What Languages Does Calais Support?
For the short term Calais is limited to English and will reject non-English language submissions. Please see the roadmap for our plans to incorporate additional languages in the near future.
What Can I Send to Calais?
Calais is optimized to process reasonably well written English prose. News articles, blog entries and other similar content all work well. Please see the roadmap for information on when Calais will support additional content types such as SEC filings, patents and others.
How Much Can I Send? How Fast Is It?
Quite a lot and pretty fast. The Calais web service will – on average – take significantly less than a second to process a sizable news article. During the beta period we’ll be limiting usage to a total of 50,000 transactions per license per day and two transactions per second. If you have a great idea that requires more processing capability than this please contact us and we can talk. After the beta period we'll be significantly increasing these usage limits - our goal is to allow users to submit as many documents as they need to every day.
I Have a Suggestion / Feature Request
There’s a special spot in the forums just for that. We’d really appreciate hearing your ideas. Please let us know at Feature Requests. You may also want to drop by the Calais roadmap to see where Calais is headed.
Bounties? Did I Hear Bounties?
Yep. It’s applications that make web services accessible to end users and we want as many people benefiting from Calais as possible. Visit the bounties page to see how we’re going about setting up a bounty program and gathering ideas.
I’m not a web-services developer. How do I try it out?
In the near future there will be a host of tools for you to use. As of today we have a couple of simple sample applications that will allow you to start experimenting. You’ll still need a developer license key available in the developers area.
I Have a Different Question!
Please start by taking a look at the Forums. If that doesn’t work for you please drop us a note.
