lucene-openrelevance-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From David Potocnik <david.potoc...@gmail.com>
Subject Re: Full document collection
Date Sun, 07 Oct 2012 18:21:28 GMT
"""
Two large datasets with tens of thousands of queries (30,000+/10,000)
were released.
136 features have been extracted for each query-url pair
"""

Great! Thank you, I'll play with this asap.

d.

On 5 October 2012 10:37, Mauro Dragoni <maurodragoni@gmail.com> wrote:
> Hi,
> if I understood correctly your problem, you should use Learning To
> Rank datasets.
> There are some very good datasets available, for example this one:
>
> http://research.microsoft.com/en-us/projects/mslr/
>
> Mauro.
>
> On Thu, Oct 4, 2012 at 7:45 PM, David Potocnik <david.potocnik@gmail.com> wrote:
>> Very interested in this as well!
>>
>> I am trying to optimize query parameters via reinforcement learning
>> (how people interact with the results), are there datasets for this?
>>
>> David Potocnik
>> --middlemachine
>>
>> On 4 October 2012 16:59, Mauro Dragoni <maurodragoni@gmail.com> wrote:
>>> Hi to everyone,
>>> I am looking for a complete document collection, freely available, containing:
>>>
>>> * full document content
>>> * queries
>>> * relevance judgments
>>>
>>> in order to test the enrichment of these documents with semantic
>>> information coming from external knowledge bases.
>>> Do you know of such a collection?
>>>
>>> I found a link to the Ancestry.com Forum Dataset collection, but I am
>>> not able to find the documents.
>>> This collection should be very interesting for my experiments;
>>> obviously others are welcome... :)
>>>
>>> Thank you in advance for any help about it.
>>>
>>> Mauro.
>>>
>>> --
>>> Dr. Mauro Dragoni
>>> Ph.D. in Computer Science.
>>> Post-Doc Researcher at Fondazione Bruno Kessler (FBK-IRST), Trento, Italy.
>>>
>>> My Research Site: https://dkm.fbk.eu/index.php/Mauro_Dragoni
>>> My Business Site: http://www.dragotechpro.com
>>> My News-Project Site: http://www.dragotimes.com
>>>
>>>
>>> Confidentially Notice. This electronic mail transmission may contain
>>> legally privileged and/or confidential information. Do not read this,
>>> if you are not the person named to.
>>> Any use, distribution, copying or disclosure by any other person is
>>> strictly prohibited.
>>> If you received this transmission in error, please notify the sender
>>> and delete the original transmission and its attachments without
>>> reading or saving it in any manner.
>
>
>
> --
> Dr. Mauro Dragoni
> Ph.D. in Computer Science.
> Post-Doc Researcher at Fondazione Bruno Kessler (FBK-IRST), Trento, Italy.
>
> My Research Site: https://dkm.fbk.eu/index.php/Mauro_Dragoni
> My Business Site: http://www.dragotechpro.com
> My News-Project Site: http://www.dragotimes.com
>
>
> Confidentially Notice. This electronic mail transmission may contain
> legally privileged and/or confidential information. Do not read this,
> if you are not the person named to.
> Any use, distribution, copying or disclosure by any other person is
> strictly prohibited.
> If you received this transmission in error, please notify the sender
> and delete the original transmission and its attachments without
> reading or saving it in any manner.

Mime
View raw message