Posted by: admin on September 22nd, 2011
Today marks the release of exciting new AlchemyAPI functionality: Relation Extraction & Directional-Sentiment Analysis.
Relation extraction identifies facts, events, buying signals, targeted customer sentiment, and more inside raw text:
Designed to power a new breed of customer opinion tracking, automated lead generation, document analysis and data visualization applications, AlchemyAPI’s relation extraction API processes natural language, converting documents and web pages into actionable, semantically enriched “Subject-Action-Object” data.
AlchemyAPI also now offers directional-sentiment analysis. This means understanding the source of an opinion and who or what it is directed towards. Here’s an example of directional-sentiment in action:
“Ugly Bob attacked beautiful Susan.”
AlchemyAPI decodes three different sentiment values for the statement above. It marks “Bob” as negative (because he was indicated as being “Ugly”), and Susan as positive (because she is “beautiful”). Additionally, using directional-sentiment, AlchemyAPI decodes the fact that Bob is emitting negative sentiment towards Susan (he is attacking her). Named entity extraction is also incorporated, so AlchemyAPI knows that Bob and Susan are both Persons.
Directional-sentiment and relation extraction expands AlchemyAPI’s significant arsenal of text-analysis capabilities, and we look forward to seeing the innovative tools and applications built by our customers and user community using these new features.
In other news: AlchemyAPI processed more than 2 billion customer API transactions last month. For those counting, this is over 700 text analysis operations every second performed by our platform. We’re excited about this continued growth and proud to see AlchemyAPI leveraged by customers in 5 continents and more than one dozen countries.
Posted by: admin on May 23rd, 2011
Today we’re announcing a significant new update to AlchemyAPI.
Over the past 2 years, our platform has earned a reputation as one of the fastest natural language processing solutions available anywhere. This release further advances the state-of-the-art, offering nearly 100% faster text analysis performance while simultaneously increasing linguistic accuracy.
Built to power a growing number of time-sensitive business applications, such as real-time stock trading and information routing, AlchemyAPI’s latest update further advances its performance lead over competing platforms, providing the ability to analyze hundreds of documents per second with extremely low latency.
Natural language processing functionality has also been significantly expanded, with the addition of new co-reference resolution capability and improved entity disambiguation functionality.
Co-reference functionality provide the ability to resolve “referent” mentions within a document back to their source entity. AlchemyAPI’s capability goes beyond the simple “he / she” heuristics found in competing systems to provide true, linguistically driven mention resolution:
Example #1:
Example #2:
Our disambiguation engine has also seen a significant update in this release, providing increased accuracy and faster performance. For more information on AlchemyAPI’s named entity disambiguation functionality, click here.
Performance and feature updates are available immediately to all AlchemyAPI users.
AlchemyAPI will also be exhibiting later this week at the 2011 GLUE conference. If you’re attending, stop by booth #7 to see what’s in store for our next release!
Posted by: admin on March 21st, 2011
Today we officially announced the release of new sentiment analysis functionality within AlchemyAPI. We have been quietly testing this new capability with a number of partners for the past few months, and are happy to make it available today to the broader AlchemyAPI community.
AlchemyAPI’s sentiment API provides a variety of features, including document-level, entity-targeted and keyword-targeted sentiment mining. We’re also supporting negation handling, sentiment amplifiers / diminishers, slang, and typos. AlchemyAPI’s sentiment engine is also fully trainable, providing easy integration into niche applications or for handling specific content types.
More information on AlchemyAPI’s new sentiment engine is available here.
In other news, AlchemyAPI will be exhibiting March 23rd at the Structure Big Data 2011 conference in NYC. If you’re attending, stop by our booth!
Posted by: admin on November 1st, 2010
We’re been super busy over the past few months rolling out new AlchemyAPI updates, SDKs, and 3rd-party integrations. Response from our new Concept Tagging API has been fantastic; we’re seeing great uptake for this feature and all sorts of new customer applications built around it.
Our customers and partners know we’ve been testing new Sentiment Analysis functionality as well, something we’re truly excited about deploying to our general user population. Named entity disambiguation and sub-type resolution has been greatly expanded, decoding hundreds of new entity sub-types (ranging from Athletes to Comic Book Artists!)
The last few months have seen a wide variety of integrations into 3rd party tools & applications: Drupal plugins, WordPress extensions, Web Browser Extensions, Data Visualization Tools, Yahoo Pipes modules, Unix/Linux command-line NLP tools, and more. One of our team’s favorites is the BBC’s experimental interactive TV system, which leverages AlchemyAPI to analyze closed captioning data in real-time, showing WWW content recommendations on your TV that are related to what’s being talked about. Have you seen or created any exciting AlchemyAPI integrations? Please tell us! We love to hear about them.
Our team at Orchestr8 has really enjoyed making premier NLP technology available to our partners and customers via AlchemyAPI, and we’re only getting started. Orchestr8 is growing rapidly, currently hiring more engineers & NLP geeks, and preparing to release some really exciting new technology in the realm of Big-Data Analytics (with a NLP twist!).
Posted by: admin on March 30th, 2010
Today we’re announcing a new AlchemyAPI release, containing significant enhancements to our Keyword Extraction API.
A new “GetRankedKeywords” API is now available, exposing relevance scores for extracted keywords. These scores represent the overall importance of a given keyword to a document.
AlchemyAPI’s Keyword Extraction API also contains a number of under-the-hood enhancements, which result in even better & more relevant keywords for your content.
We’ve released updates to the AlchemyAPI SDKs as well, exposing our new Keyword API for quick integration into your application.
Stay tuned for more updates & AlchemyAPI enhancements.
PS. — Do you love NLP, text analytics, and the semantic web as much as we do? Join our team! AlchemyAPI is now hiring for a number of positions, including linguistic annotators, QA engineers, and core NLP developers.
Posted by: admin on March 11th, 2010
To keep up with our growth for 2010, AlchemyAPI is moving into new offices! We’re now located in the heart of Denver, in the Riverpoint Building @ Confluence Park.
2010 is turning out to be a great year for AlchemyAPI. We’ve seen integration into a wide variety of third-party applications & services, including Apache UIMA, Wandora, Google Wave, and JackBe’s Presto Cloud platform. AlchemyAPI has seen thousands of new users and massive growth in daily API calls served. Recently, our product team has been previewing exciting new functionality to select customers and partners, and we will be rolling these capabilities out to our entire user community very soon.
Keep reading for more updates!
Posted by: admin on November 20th, 2009
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.
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!
Posted by: admin on October 27th, 2009
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.
Posted by: admin on October 21st, 2009
Orchestr8 will be presenting AlchemyAPI at the Boulder Semantic Web Meetup on Nov. 4th. If you’re located in Colorado and are interested in learning more about AlchemyAPI’s text analytics capabilities and how they related to the Semantic Web / RDF, come join us!
More information on this meetup is available at the following website:
http://www.meetup.com/Boulder-Semantic-Web-Meetup/
Posted by: admin on October 5th, 2009
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!
