jackrabbit-users mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Stefan Henß" <stefan.he...@googlemail.com>
Subject Re: Automatically extracted Jackrabbit FAQs
Date Tue, 08 Mar 2011 21:19:36 GMT
Hi Alex,

thanks for your interest :-)

You can ignore the comments boxes, those are only there if someone wants 
to provide a better answer for the users (when the final version will 
launch).

For my evaluation I only consider the ratings and some comments about 
the approach in general users gave in forums / mailing lists.

Considering the rating you can give as many stars as you think the Q/A 
is valuable to the reader. If it's a irrelevant question, low rating. If 
the answer is not helpful, especially low rating :-)


Best regards,

Stefan


Am 08.03.2011 22:03, schrieb Alexander Klimetschek:
> Interesting :-)
>
> But from a first glance, I am not sure how to evaluate the answers. Should
> I rate? Write a comment? Are comments only for correcting the answer (and
> thus not directly useful for your quality statistics)? What if an answer
> is wrong or a non-answering email from the mailing list thread was used -
> rate it with 1 star?
>
> Regards,
> Alex
>
> On 08.03.11 21:54, "Stefan Henß"<stefan.henss@googlemail.com>  wrote:
>
>> Hi everybody,
>>
>> I'm currently doing research for my bachelor thesis on how to
>> automatically extract FAQs from unstructured data.
>>
>> For this I've built a system automatically performing the following:
>> - Load thousands of conversations from forums and mailing lists (don't
>> mind the categories there, don't discriminate between sources).
>> - Build new categorization solely based on the conversation's texts (by
>> clustering).
>> - Pick the best modelled categories as basis for one FAQ each.
>> - For each question (first entry in a thread) find the best reply from
>> its answers.
>> - Select the most relevant and well formatted question/answer-pairs for
>> each FAQ.
>>
>> For the evaluation I'm interested in expert's perceptions of the
>> results, e.g. if the questions are relevant, correctly answered, etc.
>> Also as I'll release a paper about the approach I'd be happy if you
>> could rate one or two questions (stars on the details pages) so I'd have
>> some statistics to present.
>>
>>
>> Here's the direct link to the Jackrabbit FAQs:
>> http://faqcluster.com/jackrabbit-node-jcr-repository-apache
>>
>> (There are some other interesting FAQs as well at http://faqcluster.com/)
>>
>>
>> Thanks for your help
>>
>> Stefan
>>
>


Mime
View raw message