I was surprised by this mention and inclusion in this set of trading cards, and I posted this to my "Bill Slawski" Google Plus page, but I wanted to post it here to, to make sure that anyone following this page also looks up some of the other people who are included in this collection.
Paraphrase-Driven Learning for Open Question Answering
Here's the abstract to the paper:
We study question answering as a machine learning problem, and induce a function that maps open-domain questions to queries over a database of web extractions. Given a large, community-authored, question-paraphrase corpus, we demonstrate that it is possible to learn a semantic lexicon and linear ranking function without manually annotating questions. Our approach automatically generalizes a seed lexicon and includes a scalable, parallelized perceptron parameter estimation scheme. Experiments show that our approach more than quadruples the recall of the seed lexicon, with only an 8% loss in precision.
A nice thoughtful discussion about the future of search in days when deep learning, more processing power, and smarter computers start showing us search results, sometimes before we even ask for them.
I had a chance to participate in this post, but it's worth a look for the other viewpoints as well. What do you see the future of search looking like when computers move towards more intelligent and informed results?
Right, the old "hair of the dog" query, and how engines will determine if a searcher is looking for a dog hair brush or a Bloody Mary. It's all really fascinating and I'm really looking forward to seeing how results (and searches for that matter) will evolve. I do believe you're right, and that there will be multiple factors taken into consideration when delivering results.
Bill Slawski is simply one of the sharpest smartest SEO's in the world. His publications on his blog, SEOBYTHESEA, present more in depth information about how the search engines are thinking and what they are likelier to be doing than is available anywhere else. I started following him around 2004 and he identified key changes in Google, and I'm still following him in 2011 and he is identifying changes that continue to work. Really one of the best in the world