Vertical selection is the task of selecting the relevant verticals, if any, in response to a user's query. We focus on single vertical selection, defined as the task of predicting a single relevant vertical.
They looked at 18 different verticals and compared how their vertical selection methods compared with prior work on federated search. They used:
- Query string features which used key phrases in the query ("weather", "movies", etc...)
- Query log features which used the likelihood of the query given past queries on the vertical
- Corpus features which uses documents retrieved from the different verticals.
My congratulations to Jaime, Fernando, Jamie, and Jean-Francois!
(Note: Since the best paper was from a student there was no separate best student paper award)
Could you please post a link to the paper?
ReplyDeleteThanks!
Bart J
Neither the authors nor the ACM have made it available online yet.
ReplyDeleteIt will be online soon and I'll add a link.
I found it on ACM's DL
ReplyDeletehttp://doi.acm.org/10.1145/1571941.1571997
Thanks for the kind publicity Jeff. It was good to meet you. Jaime.
ReplyDeleteOk, the paper is posted online, at http://www.cs.cmu.edu/~jaime/. cheers, jaime
ReplyDeleteThanks Jaime, I've updated the link to the open copy.
ReplyDeleteIt was great seeing you. Hopefully we can get a chance to hang out more soon.