[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
You can skip relevance feedback question. e: CSE 494 H/W
- To: Mary Forsberg <mforsber@asu.edu>
- Subject: You can skip relevance feedback question. e: CSE 494 H/W
- From: Subbarao Kambhampati <rao@asu.edu>
- Date: Thu, 15 Sep 2011 19:19:48 -0700
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:date:x-google-sender-auth:message-id:subject :from:to:content-type; bh=z7CnJUYBPi8ELf2H9EfNkTg5BzdOLNSGQogdCPs5uG4=; b=lWpw4ix/z+j1jKU9KnmWhwrkLcGRVUwUeGDcvBCcRkINWCm91+8gFqlaAnitzLeKKl e/8ZQHG1jSAqzqJUuK0aO5RftnP2kOMb/sJB73Wqs76+t3dtpvfa2ITyNsVdqSdlyMEZ ESKzob4A6VM90qH0JvOi2LCtypWK6uBejIWEY=
- Sender: subbarao2z2@gmail.com
Since we havent formally covered relevance feedback, you can skip it.
Rao
On Thursday, September 15, 2011, Mary Forsberg <mforsber@asu.edu> wrote:
> Hello Dr. Rao,
> In calculating the relevance feedback using Rocchio
> method for part 4 of problem 2, do we consider
> the document collection to be the same
> original 10?
> Or is the collection of relevant documents {d4,d6}
> irrelevant documents {d4}
>
> Additionally, is a negative value in the Query vector
> set to zero in this feedback model?
>
> Also, do we need to use the alpha, beta, gamma values in the
> Rocchio equation.
>
>
> Since the table of tf/idf vectors was incomplete
> I wondered if I misunderstood the problem
> parameters.
> Thanks for any clarification,
> Mary