Venue: Internet
Grant Ingersoll, founder and CTO of LucidWorks, talks with Tobias Kaatz about his book Taming Text: How to Find, Organize, and Manipulate It. They begin by discussing popular existing systems for the automated understanding of contextual information. One such system, IBM Watson, drew attention for its victory in the “Jeopardy” game show. They proceed to discuss Google Now and Siri, which take on the challenge of multiple languages and demonstrate the capabilities and limitations of this type of technology.
The second part of the interview focuses on related methodologies from the latter part of the book, including “fuzzy string matching” and “entity recognition,” and their application to real world problems. The discussion wraps up as of the episode as Ingersoll and Kaatz look at challenges the search community is facing right now such as building Q&A systems and understanding natural language across language barriers.
Show Notes
Related Links
- IBM Watson: http://www.ibm.com/smarterplanet/us/en/ibmwatson/
- LucidWorks: http://lucidworks.com
- “Eugene Goostman” passing turing test: http://mashable.com/2014/06/12/eugene-goostman-turing-test/
- Siri: https://www.apple.com/ios/siri/
- Google Now: https://www.google.com/landing/now/
- Lucene: https://lucene.apache.org/
- Mahout: https://mahout.apache.org/
- Apache Solr: https://lucene.apache.org/solr/
- Apache OpenNLP: https://opennlp.apache.org/
- IBMs neurosynaptic chips: http://www.research.ibm.com/cognitive-computing/neurosynaptic-chips.shtml
- Andrew Ng et. al : “Map-Reduce for Machine Learning on Multicore”: http://www.cs.stanford.edu/people/ang//papers/nips06-mapreducemulticore.pdf
- Apache Spark™: https://spark.apache.org/
- Lucene/Solr Revolution Conference: http://lucenerevolution.org/
- Taming Text (book): http://www.manning.com/ingersoll/
- SE Radio episode 187 on Apache Solr Search Engine: https://www.se-radio.net/2012/07/episode-187-grant-ingersoll-on-the-solr-search-engine/
- SE Radio episode 193 on Apache Mahout: https://www.se-radio.net/2013/04/episode-193-apache-mahout/