Today we’re announcing both a new AlchemyAPI service update, and a totally revamped AlchemyAPI.com website design.

The AlchemyAPI service update contains several notable enhancements:

• URL Link Un-Shortening - Links are automatically un-shortened for any URL content submitted for one of the 80+ URL Link Shorteners currently in existence (bit.ly, tinyurl, etc).  API responses now include un-shortened URL information.

• CrunchBase Integration - Named entity API responses now include linkages to CrunchBase entries for thousands of technology and startup companies.  Semantic CrunchBase support has also been included.

• Named Entity Disambiguation Updates - Increased coverage (30%+ increase in disambiguation coverage) and increased precision (more accurate entity disambiguations)

Here’s a peek at the new AlchemyAPI.com (kudos to our designer, Archie, for doing a great job!):

Some truly exciting things are in the pipeline for AlchemyAPI in Q4 of 2009; keep watching for the next update!

Today we’re announcing a second AlchemyAPI release for the month of October.  This update
includes several new features & enhancements:

Quotations Extraction - AlchemyAPI now identifies quotations in any unstructured text, such as newswire  articles or blog postings.  Using quotations extraction, AlchemyAPI exposes both what is being said, and  who is saying it.

Coreference Resolution - AlchemyAPI now resolves he/she/his/her/etc coreferences into named entities, providing a more comprehensive view of processed texts.

This latest AlchemyAPI release also contains a number of under-the-hood enhancements to Terminology Extraction and other APIs.  New functionality is available effective immediately to all existing AlchemyAPI users.

Another AlchemyAPI release is upon us.  This is a maintenance release contains a variety
of enhancements:

Increased Precision - Named Entity Extraction now features increased precision for all English-language content.  This means fewer false positives & more accurate results.  Recall has also been increased, meaning you’ll get more named entities when submitting content.  These updates will roll out to our other supported languages over the next two weeks.

Disambiguation - Named entity disambiguation coverage has been greatly expanded; AlchemyAPI’s disambiguation database has more than doubled in size, providing much greater coverage for non-USA locations, persons, organizations, and more.  We’ve also increased disambiguation accuracy, meaning more accurate results when processing ambiguous texts.

Web Page Cleaning - AlchemyAPI’s text extraction / web page cleaning APIs have been updated; Text extraction now operates with increased precision, especially for Blogs and other non-News content types.

AlchemyAPI is among the most accurate and highest performance content analysis APIs in the industry.  This release is part of our continued commitment to advancing text analysis precision, recall, and performance. We have more exciting AlchemyAPI news & feature enhancements planned for the month of October.  Stay tuned!

AlchemyAPI recently celebrated its one year anniversary in operation; over the past twelve months, we’ve enjoyed becoming critical infrastructure for a number of leading companies in the content aggregation, social media monitoring, and contextual advertising verticals.

Today, our platform analyzes massive quantities of information each day.  AlchemyAPI has enjoyed 10 major releases in the past year, and now supports 8 major languages.

Since AlchemyAPI’s initial launch, our user community has played a pivotal role in the development of this service.  We love receiving requests from our community, and user feedback is heavily leveraged in our product planning / roadmap process.

Today, we’re happy to announce that AlchemyAPI usage limits have been raised for all users:

Those in our “Free” service tier have had your usage limits tripled, from 10,000 daily transactions to 30,000 !

Transaction limits for our Basic, Professional, and Metered tiers have also been raised.

This is a way of saying “thanks” to our terrific user community.

Here’s to another fantastic year for AlchemyAPI!

Orchestr8 has signed on as a sponsor / exhibitor at this year’s Location Intelligence Conference.
If you’re planning on attending, stop by our booth (#11) where we’ll be demoing AlchemyAPI’s
advanced geo-tagging capabilities.

For more information on this event, click here.

About this conference (now in its 6th year):

Location Technology is everywhere in the Enterprise…

From managing telecommunications, to mitigating terrorist threats, to locating
retail stores as well as finding the most efficient routes for supply chain management,
location technology is driving business effectiveness. In this economic climate, the
location intelligent company will survive and thrive.

Anyone interested in attending this event (Oct 5-7) may click here for registration information.

We’re announcing another significant update to the AlchemyAPI content analysis service: Visual Constraints Web Content Mining

This is an entirely new AlchemyAPI capability that enables extraction of structured data (product information, pricing, descriptions, etc.) from any web page.  Visual constraints enable content extraction using simple ‘natural language’ queries, such as: “all links after product details”

Pictures speak louder than words, so here are some query examples:

AlchemyAPI’s visual constraint query engine is a powerful tool for extracting structured data from any web page. Constraints enable content to be identified using visual characteristics such as text labels & patterns, positioning within a web page, structural encapsulation, and more. Mining structured data via visual constraints is robust against changes in underlying HTML document / tag structure, CSS, etc.

Something else we’re really excited about: Visual constraints are fully integrated into AlchemyAPI’s other content analysis capabilities, enabling the targeted execution of named entity recognition, text categorization, language detection, or other NLP tasks on specific portions of a web page.  AlchemyAPI is unique in the industry with this capability to perform highly-targeted NLP operations on web pages.
AlchemyAPI also now fully supports XPath, for the W3C / XSLT fans out there.

Here’s an example of targeted named entity extraction operations:

We’ll be exploring more in coming weeks regarding using AlchemyAPI’s visual constraints engine to perform targeted named entity & keyword extraction, topic categorization, language detection operations, and more.

AlchemyAPI has been growing at an amazing pace over the past year since our first public release.  We’re processing a massive number of API calls each day, for a variety of customers in multiple industry verticals.

We love engaging with our customers and user community, gathering feedback regarding our service and suggestions for improvement.  This community feedback has a direct impact on our product planning and the general direction of AlchemyAPI.

This new AlchemyAPI release brings a new feature requested by a number of you in our community:

Relevancy Ranking

Relevancy ranking expands upon AlchemyAPI’s sophisticated named entity extraction capability, applying a numeric ‘relevancy score’ to every item we detect.  These scores convey the importance of a given entity (Person, Company, etc.) to the document being processed as a whole.

Relevancy ranking enables one to easily sift through the named entities within a given news article or other piece of content, identifying what’s important and what isn’t.

Our relevancy functionality employs a sophisticated statistical ranking algorithm, employing over two-dozen different signals & cues, as well as advanced probability modeling. It provides far superior results to frequency/count-based relevancy ranking approaches.

This AlchemyAPI release also offers increased named entity extraction precision. This means fewer false positives and better extraction results.  Give our system a whirl and you’ll find it’s among the most accurate in the industry!

Stay tuned for more updates!

Another AlchemyAPI release is upon us, providing a significant update to our “automatic language identification” capability, new performance and character encoding enhancements, and more!

AlchemyAPI utilizes statistical and lexical techniques to automatically determine the language of any content it processes.  Our natural language processing core leverages this information to provide increased accuracy when categorizing text, extracting keywords and named entities, and so on.

Our new automatic language identification capability represents a huge leap in functionality; AlchemyAPI is now capable of identifying content written in 97 different languages!  This includes nearly all of the world’s major languages, in addition to uncommon / regional dialects such as Cherokee, Dakota, and Macedonian, etc.

AlchemyAPI’s language detector is extremely robust, capable of generating a match from only a few words of text.  It operates at a high level of precision, and is extremely fast.  We detect more languages, with better accuracy, than any other language detection service in the industry today.

An interactive demo of our language detector is available here.

Our language detection API now also returns additional data: ISO-639 language codes, links to language information on Ethnologue and Wikipedia, the number of native speakers for each language, and more!

If you are currently doing language / information-extraction research, are a linguist, or are working with a language that we do not currently support, we’d love to hear from you.

We’re back this month with another big AlchemyAPI service update!  This release includes a number of under-the-hood enhancements that further enhance the performance and usability of AlchemyAPI.  Also now available, a significant new text analysis capability:

Automated ‘Concept’ Tagging / Phrase Extraction

Concept tagging is a text analysis technology that works in conjunction AlchemyAPI’s Named Entity Recognition (NER) capability, to discover tags, phrases, and specific terminology that relate to the “about-ness” of a piece of content.

This new tagging capability is the result of months of behind-the-scenes engineering effort, and employs some relatively sophisticated statistical analysis and language modeling techniques.

Our new tagging system also works in 8 different languages, more languages than any other automated tagging service, commercial or otherwise.  Feel free to push English, French, German, Russian, Italian, Spanish, Portuguese, or Swedish content through the system.

So what kind of tags can this system extract?  Here’s an example:

Article: “NASA celebrates Chandra X-Ray Observatory’s 10th anniversary”

Extracted Tags / Phrases: chandra x-ray image, chandra data, chandra project, hubble space telescope, science mission directorate, nasa headquarters, space shuttle columbia, dark matter, …

It’s worth noting that our Concept Tagging system is robust when processing specialized content (such as scientific publications) as well as more general content (news & blogs).

To try an interactive demo of Concept Tagging, click here.

Today we’re announcing a significant upgrade to our AlchemyAPI content analysis online service. This update includes expanded language coverage (adding Portuguese and Swedish), enhanced text categorization, and integration with Linked Data standards.

The press release for this update is available here.

AlchemyAPI now supports analyzing content written in eight different languages, more than any other commercially-available text mining service.   We’re committed to supporting all of the world’s major languages, and this update moves us significantly closer to that end-goal.  AlchemyAPI now understands the native language of over 1.2 billion individuals.

Significant updates have also been made to AlchemyAPI’s text categorization service, a mechanism that identifies content by subject category (health, politics, etc.). Support for five new subject categories, enhancements to categorization performance, and support for processing Microblogging content have all been integrated into this release.

AlchemyAPI enters the “Semantic Web” world with integrated support for Linked Data standards. By interconnecting with assets in the Linked Data cloud, publishers gain access to a huge volume of highly-relevant information, further enhancing the value of their content.  AlchemyAPI integrates content links to online databases such as Wikipedia, GeoNames, the CIA World Factbook, and more. Linked Data integration also includes support for RDF (Resource Description Format) semantic web standards.

These updates are available immediately to all new and existing AlchemyAPI subscription users. To learn more about AlchemyAPI, please visit http://www.alchemyapi.com/.