Author Archives: Tal Rotbart

This is a bit of a belated blog post, but we wanted to get our winner’s permission to share his fascinating story along with announcing his win.

Those of you who follow our blog would know that we were one of the prize sponsors at Semantic Hack in San Francisco at the beginning of the month.

We’d like to offer a big congratulations to Scott C. Smith on his win!

We’d like to offer a big congratulations to Scott C. Smith on his win!

Scott took home a $500 Amazon.com gift card and $12,000 worth of usage of our API for a year. He won this prize for his still in-progress iPhone app with which students could play with words by discovering the funny juxtapositions of multiple meanings.

Following the Hackathon, we got in touch with our winner to arrange the delivery of his hard-won loot, which is when we came to learn of his story.

Last year at this time, I had never heard of an API. I was a school teacher looking for a way to get paid doing what I love, which is looking at maps.

“Last year at this time, I had never heard of an API. I was a school teacher looking for a way to get paid doing what I love, which is looking at maps.” Scott revealed to me in the eMail thanking me for the prize.

While participating in an iOS programming bootcamp, Scott came up with his idea for an app which allows exploring one’s surrounding by identifying Wikipedia articles that describe locations nearby.

“I described my idea of letting people touch a location on a map as a way of learning more about it, by having Wikipedia articles appear, for instance.”

“My instructor thought that would be possible and asked if Wikipedia had an API. That was the first I’d heard the term, so I discreetly Googled it.”

Scott spent all of last fall perfecting his application, tracking down the right APIs to use and becoming familiar with websites for software developers.

This culminated in the release of his app, TapAMap on the Apple App Store in January.

Scott got into semantics when he attended a presentation by Eric Franzon, VP Community at SemanticWeb.com.

“I went to the [Semantic Hack] hackathon, but felt a little intimidated by all the PhD hard-core coders. I wasn’t the only newbie, though. I talked to some folks about my question of which would be the best ontology editor for someone like me to play with as a way of learning.”

[I] was attracted to SpringSense because you provided what for me was an easy way to access it.

“By the time I was done with that, most of the hacking groups had formed and were hunched over their laptops or busily exchanging ideas. So I sat by myself and began reading about each of the sponsors. I played with the APIs to get a sense of what they could do, and was attracted to SpringSense because you provided what for me was an easy way to access it.”

As a lover of language, Scott was was attracted to the disambiguation possibilities: “I started to dream up an iPhone app (since that’s all I can do at this point!) with which students could play with words by discovering the funny juxtaposition of multiple meanings.”

We’ll keep you posted about Scott’s progress on his iPhone app. We’re very keen to play with it ourselves!

The SpringSense Meaning Recognition API is available now with a FREE usage tier on Mashape.

We’ve had a busy weekend for the SpringSense Meaning Recognition API, with three Hackathons around the world featuring v2 of the API.

First was APIDays Mediterranea‘s warm up Hackathon at Madrid@Rails, then Semantic Hack in San Francisco and AngelhackNYC in New York City.

We were proud prize sponsors for the latter two, with the Best Use of the SpringSense API Prize comprising of a $500 Amazon.com gift card and a $12,000 worth of API usage over a year — a total prize value of $12,500.

We’d like to congratulate Lance Nanek who won our Angelhack NYC prize. Lance combined Google Glass, an Android handset and the API to create a very cool app to help nurses in their role. See his demo here.

Special thanks to Mashape, our API hub for their support in getting the API into the hands of the Hackathon developers.

The API is available now on Mashape with a free usage tier.

Those of you familiar with the SpringSense story will be aware that until recently, SpringSense held the title of the world’s most accurate noun-sense disambiguator, and delivered this accuracy in real-time.

In the July/August 2012 issue of IEEE Intelligent System, an academic paper from P. Chen, C. Bowes (Uni. of Houston) and W. Ding, M. Choly (Uni. of Massachusetts, Boston) described a technique that was able to surpass the accuracy of version 1.0 of our technology. Whilst unable to perform the task quickly enough to be useful to enterprise, we still didn’t like the idea of being number 2, so we set about reclaiming the title.

We still didn’t like the idea of being number two, so we set about reclaiming the title

The mission we charged our chief scientist with, was to do whatever it took to regain top position; Fred Rotbart, PhD, was told nothing was off-limits. In our early sessions as we investigated the possibilities, it quickly became clear that the basis of our existing approach was valid as it offered us real-time speed, something we couldn’t sacrifice if we wanted a solution that could be used by our customers in enterprise.

A way forward presented itself; our innovative approach to NLP was valid, but we needed to re-visit our implementation. Dr Rotbart proceeded to pull apart our algorithm, and put it back together well oiled and with less cruft, which edged us closer to our goal. Our big breakthrough though, came after a moment of insight from Dr Rotbart, leading him to find an alternative and more accurate way of using the results of our data-mining algorithm to perform the noun-sense disambiguation.

The result was an increase in accuracy to a world leading 83.4%, as measured by the industry and academic benchmark SemEval 4 (task 7), without sacrificing any of the performance that allows SpringSense to be used for high volume transactional usage, such as Big Data and enterprise search.

Being overtaken by a more accurate solution was a useful learning experience for us as a team. What we learned from the journey was that to be useful to our customers, a solution needs to work in real-time without sacrificing accuracy. Our mission here in the SpringSense team remains to lead the world in both speed and accuracy.

The new version with the accuracy improvements is already live on the Mashape API Hub, we’d love for you to try it out and give us your feedback; a free plan is offered for your evaluation. Bindings are available for Ruby, Python, Java and ElasticSearch and more.

Melbourne Solr/Lucene Users Group Logo

Melbourne Solr/Lucene Users Group Logo

Here at SpringSense we’ve noticed that there is a blossoming of Apache Solr/Lucene usage and development in Melbourne, but we’re missing an unofficial, relaxed gathering to allow some fruitful information and experience exchange.

We’re trying to put together a laid back meet up for developers (and other interested people) who are currently using Apache Solr (and/or Lucene) or would like to learn more about it. Aiming for it to be a high signal/noise ratio group, with meet ups probably once every two months.

The first meet up is still TBD, but please join the group if you’re keen to join us for pizza, beer, and a discussion about Solr once we figure out the date of the first meeting.

Also, please feel free to suggest quick (15 minute) presentations - whether it be a problem you’ve solved, a problem you need help solving or a general interesting experience of using Solr.

We’re keeping registrations here: http://www.meetup.com/melbourne-solr/

Feel free to pass to co-workers, colleagues who would be interested.

Back from the Big Apple!

Well after some VERY long flights we’re back from a great week in New York City and the successful launch of SpringSense at Enterprise Search Summit Spring 2011. It was great to meet and talk to so many search professionals and share our passion for a better way to search.

We had some productive meetings and have some exciting developments in the pipeline; all we can say for the moment is watch this space.

Highlights from the conference include meeting Eric Reiss after his keynote speech, “The Dumbing Down Of Intelligent Search”. Hopefully the organisers will post a copy of the presentation online- we’ll put up a link to it when they do.

And finally a big congratulations to Robert Boeri on winning the 24″ LCD HDTV giveaway; it couldn’t have gone to a nicer bloke.

Our booth at the Enterprise Search Summit 2011

Our booth at the Enterprise Search Summit 2011

It’s the day before, and our humble booth is all set-up at the Enterprise Search Summit in New York City. If you’re around we’d love to see you and have a chat!

I’m very happy to confirm that we are Gold Sponsors for the Spring 2011 Enterprise Search Summit in New York City on May 10-11th — come visit us at booth 19.