Mr. DLib v1.2.1 released: Improved keyphrase extraction and Apache Lucene query handling

The new version of Mr. DLib completes 104 issues. The most notable ones are: We improved the keyphrase extraction, i.e. keyphrases are no stored differently in Lucene. We expect a better recommendation effectiveness and are currently running an A/B test. More robust path encoding for search queries (special characters in a URL caused errors) Lucene’s eDismax function […]

New recommendation algorithms integrated

We have integrated several new recommendation algorithms into Mr. DLib. Some algorithms are only ought as baselines for our researchers, others hopefully will further increase the effectiveness of Mr. DLib. Overall, Mr. DLib now uses the following algorithms: Random The approach randomly picks the set of documents to recommend to the user. We experiment with this […]