Re: [Wikimedia-l] Update on Discovery Projects

2017-06-16 Thread Trey Jones
Hi Jim, Determining the intent of a particular search is indeed very difficult, and is not really feasible to even attempt it at the scale needed for machine learning (unless you have an immense budget like some for-profit search engine companies). For our machine learning training data, we use

Re: [Wikimedia-l] Update on Discovery Projects

2017-06-16 Thread James Salsman
Hi Trey, Thanks for your very detailed reply. I have a followup question. How do you determine search intents? For example, if you see someone searching for "rents" how do you know whether they are looking for economic or property rents when evaluating the quality of the search results? If

Re: [Wikimedia-l] Update on Discovery Projects

2017-06-15 Thread Deborah Tankersley
James Salsman wrote: How will the Foundation's approach to machine learning of search > results ranking guard against overfitting? Overfitting, for those who aren't familiar with the term, describes the situation where a machine learning model inappropriately learns very specific details about

Re: [Wikimedia-l] Update on Discovery Projects

2017-06-13 Thread James Salsman
On Wed, Jun 14, 2017 at 5:25 AM, Deborah Tankersley wrote: > > The Discovery team structure has now changed, but the new teams will still > work together to complete the goals as listed in the draft annual plan.[2] > A summary of their anticipated work, as we finalize

[Wikimedia-l] Update on Discovery Projects

2017-06-13 Thread Deborah Tankersley
Hi everybody, (With apologies for cross-posting...) You may have seen the recent communication [1 ] about the product and tech tune-up which went live the week of June 5th, 2017. In that communication, we promised an update