Textkernel's move to Elasticsearch (and more)
Details
Hi all, hope you have had a good summer.
To kick off the new meetup season, Textkernel (http://www.textkernel.com) have gracefully agreed to share the lessons they have learned migrating their search solution to Elasticsearch. Textkernel is one of the few companies I know that actually do and understand Natural Language Processing and information retrieval. I'm super curious to hear their story.
As always, we will start at 18:30, with pizza and beer, followed by the talk.
Hope to see you all there,
Boaz
Abstract
As the leader in Semantic Recruitment Technology, Textkernel is set on perfecting the document understanding as well as handling of complex queries on highly structured data. In this talk, Textkernel will give a short overview of their technologies, go over the transition process from their previous search engine to Elasticsearch and highlight their use of Explain API to provide query match indication to the end user.
In the first part, Darko Zelić will talk about the motivation behind the engine switch, reasons for picking Elasticsearch, transition highlights (what went well, what went wrong) and the impact on the customers.Later, Henning Rode will go in detail about result explanation to users. He’ll show why result explanation is an important aspect of Textkernel’s search interface and how we use Elasticsearch’s Explain API efficiently for that purpose.
Bios
Darko Zelić is a core product developer and a recognised innovator at Textkernel. When he's not busy creating award-winning prototypes, he's working on improving Textkernel's flagship semantic search application, Search!. Even as a technology agnostic and a programming polyglot, he gravitates towards Java, JavaScript and PHP. Based in Amsterdam, he's a big fan of hackathons, craft beer, digital photography and black metal. Twitter: @dachaz
Henning Rode is lead search developer at Textkernel. After finishing his PhD and a PostDoc position about semi-structured document retrieval, he switched to industry for developing efficient and innovative search solutions with the Textkernel team. He is currently diving into learning to rank approaches to further improve the relevancy of search results. Besides, programming he loves canoeing, hiking, and singing in choirs.