tag:blogger.com,1999:blog-6043705792807544709.comments2023-08-09T10:46:25.007+01:00TerrierTeamTerrier Team @ Glasgowhttp://www.blogger.com/profile/11678159696002044810noreply@blogger.comBlogger68125tag:blogger.com,1999:blog-6043705792807544709.post-66334344544619964232010-07-19T20:00:49.636+01:002010-07-19T20:00:49.636+01:00The ranking is for the "past five years"...The ranking is for the "past five years". Salton hasn't obviously published in the last five years.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-49171303031949938902010-07-19T18:46:02.083+01:002010-07-19T18:46:02.083+01:00Thank you for the link. Looks reasonable with a fe...Thank you for the link. Looks reasonable with a few exceptions. E.g., where is Salton??LBhttps://www.blogger.com/profile/09673316625914340031noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-1867125870584376372010-06-05T14:59:52.007+01:002010-06-05T14:59:52.007+01:00@random The Blog track wiki provides a precise tim...@random The Blog track wiki provides a precise timetable:<br /><br />http://ir.dcs.gla.ac.uk/wiki/TREC-BLOG<br /><br />In particular, it indicates when the runs are due, and when we the common baseline runs will be made available.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-87120397253060222542010-06-02T11:57:41.870+01:002010-06-02T11:57:41.870+01:00Can you please tell me when will be the baseline r...Can you please tell me when will be the baseline runs available?randomhttps://www.blogger.com/profile/07308383554052564375noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-36123459114625958772010-04-02T09:47:02.862+01:002010-04-02T09:47:02.862+01:00@All: the web server might have been down during p...@All: the web server might have been down during part of last week-end. It has been fixed since then.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-37867831890128168532010-03-28T11:38:05.407+01:002010-03-28T11:38:05.407+01:00is there any problem with new terrier site?
I have...is there any problem with new terrier site?<br />I have been trying it but not openingUnknownhttps://www.blogger.com/profile/09001698828170417950noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-14090189870960565042010-03-18T15:57:02.205+00:002010-03-18T15:57:02.205+00:00@All Yes, the introduction of the two-stage submis...@All Yes, the introduction of the two-stage submission procedure is meant to facilitate the participation of groups who cannot necessarily index the Blogs08 collection. Like in TREC 2008, several runs will be distributed as common baselines. <br /><br />We have not worked out the precise timescale yet (this is progressing), but we expect that these baselines should be available during early summer.<br /><br />Indeed, it is good idea to have the baselines runs for both 2009 and 2010 topics.<br /><br />Note that you can obtain last year's submitted runs from the TREC web site.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-27124393309277990992010-03-18T15:22:09.860+00:002010-03-18T15:22:09.860+00:00Ahh also one thing to add .. of course this baseli...Ahh also one thing to add .. of course this baseline would be for topics of both i.e. TREC 2009 n TREC 2010? non??Unknownhttps://www.blogger.com/profile/09001698828170417950noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-16692718297268377172010-03-18T15:20:24.522+00:002010-03-18T15:20:24.522+00:00A question on TREC Blog 2010:
Are you providing B...A question on TREC Blog 2010:<br /><br />Are you providing Baselines this year like you did for TREC 2008 so that people not having facility to index such a large collection can also participate. If Yes, then when you will provide? It will be one baseline or many?? <br /><br />ThanksUnknownhttps://www.blogger.com/profile/09001698828170417950noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-81083498251730686932010-03-11T10:47:13.876+00:002010-03-11T10:47:13.876+00:00@Gul. Indeed, that was the general consensus durin...@Gul. Indeed, that was the general consensus during the blog track workshop at TREC. People thought that there is much more to do to have a good understanding of the current three facets, and it would make sense that we stick to them in the meantime, especially that there are now some training topics associated to these three facets.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-10938809436069497652010-03-10T21:30:18.438+00:002010-03-10T21:30:18.438+00:00I dont think people would like to have more facets...I dont think people would like to have more facets. Let us get more used to facets we r currenly using. Now when we are understanding the things better, we cannot go for more facets :=)Unknownhttps://www.blogger.com/profile/17235998316386166520noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-85075269382399306922010-03-10T19:18:28.324+00:002010-03-10T19:18:28.324+00:00To allow people to use last year's topics for ...To allow people to use last year's topics for training, we will very likely be using the same facets as in 2009, i.e. Opinionated, Indepth, and Personal. However, if people want to see more facets, then we are happy to consider it.<br /><br />In all cases, we will have many more topics this year than in 2009.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-70612985305230015752010-03-10T16:46:08.220+00:002010-03-10T16:46:08.220+00:00How many further Facets this year are to be added ...How many further Facets this year are to be added ???Unknownhttps://www.blogger.com/profile/09001698828170417950noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-9840876203926685922010-02-15T07:37:17.996+00:002010-02-15T07:37:17.996+00:00Thanks for the response, Iadh!
Following you on T...Thanks for the response, Iadh! <br />Following you on Twitter as well now... :-)Nimmyhttps://www.blogger.com/profile/11227810353203036224noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-74423914706918635942010-02-11T11:35:44.703+00:002010-02-11T11:35:44.703+00:00Hi Nimmy,
All information about CIKM 2011 will be...Hi Nimmy,<br /><br />All information about CIKM 2011 will be posted in due course in http://www.cikm2011.org<br /><br />In addition, if you have a Twitter account, you can follow us in:<br /><br />http://twitter.com/cikm2011<br /><br />We will be using Twitter to advertise call for papers, etc.<br /><br />We have also a CIKM 2011 Facebook group, which you are welcome to join.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-57197367537644843262010-02-10T03:32:34.127+00:002010-02-10T03:32:34.127+00:00Congrats! Looking forward to more information on t...Congrats! Looking forward to more information on the call for papers. I think I may have a good case study to share and would love to have the opportunity to do so at CIKM.Nimmyhttps://www.blogger.com/profile/11227810353203036224noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-17916564765745052322009-08-04T21:09:33.641+01:002009-08-04T21:09:33.641+01:00It was a pleasure and thanks again for the great s...It was a pleasure and thanks again for the great suggestions!Duncan McDougallhttps://www.blogger.com/profile/06662063389408020091noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-18948687063220283972009-08-04T20:26:22.723+01:002009-08-04T20:26:22.723+01:00Duncan, great chatting with you at SIGIR, and look...Duncan, great chatting with you at SIGIR, and looking forward to seeing your system evolve. I know too well that it's a lot easier to suggest enhancements than to actually implement them!Daniel Tunkelanghttps://www.blogger.com/profile/10240432137428080022noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-71706436233563330612009-07-27T11:08:04.829+01:002009-07-27T11:08:04.829+01:00Link to "Usefulness of Click-through data in ...Link to "Usefulness of Click-through data in Expert Search" is broken - should be <br />http://www.dcs.gla.ac.uk/~craigm/publications/macdonald09exclicks.pdf<br /><br />Cheers,<br />Moshe KrancUnknownhttps://www.blogger.com/profile/12492905784017729365noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-88718908939124123432009-06-05T09:00:23.305+01:002009-06-05T09:00:23.305+01:00Thanks Pavel.
Yes, indeed, table conversation was ...Thanks Pavel.<br />Yes, indeed, table conversation was helpful!Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-88323969729678598962009-06-04T17:18:25.858+01:002009-06-04T17:18:25.858+01:00Congratulations! That table conversation was fruit...Congratulations! That table conversation was fruitful :)Pavel Serdyukovhttps://www.blogger.com/profile/01890719805383154426noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-39818811246549302822009-05-12T14:53:00.000+01:002009-05-12T14:53:00.000+01:00Jon,
These are indeed very good points.
We shoul...Jon,<br /><br />These are indeed very good points. <br />We should indeed separate facet accuracy classification from relevance, and I believe that this would be possible/doable. It is pretty much how we addressed the opinion finding task. <br /><br />The relevance assessments for the blog distillation task this year will be performed by NIST. <br /><br />We are still working on the details. Your feedback on the issue is very much appreciated.Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-38443306753627273982009-05-05T20:35:00.000+01:002009-05-05T20:35:00.000+01:00don't know if we're going to participate this year...don't know if we're going to participate this year. I've got a busy summer and am getting interested in the relevance feedback track also, but this does seem like an interesting task.<br /><br />If a relevant document is returned, but with the wrong facet value, would that count as non-relevant? Will you report facet accuracy as well as relevance? <br /><br />At least for the example in the guidelines, relevance evaluation is being conflated with facet classification evaluation.<br /><br />What is the motivation behind conflating these two evaluations, rather than reporting MAP and accuracy? I realize a user would see only a single ranked list, possibly filtered by facet value, but from the participants' perspective we might like to understand whether our system is failing on the relevance ranking or the facet value assignment.Jonhttps://www.blogger.com/profile/14308358891592822280noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-70726587723131480402009-05-05T18:10:00.000+01:002009-05-05T18:10:00.000+01:00Hello Jon,
Glad that you like the new tasks. We a...Hello Jon,<br /><br />Glad that you like the new tasks. We are also trying to make sure that we have realistic queries from a query log (I prefer to use the adjective 'realistic' instead of 'representative').<br /><br />There is an example topic on the Blog track wiki. <br /><br />The facets are not necessary binary. It is possible to have more elaborated facets, e.g. +ve opinionated, -ve opinionated, balanced, non-opinionated. <br /><br />If the facet is binary, say gender, the system will produce two ranked lists for each query. <br /><br />Will CMU be participating in the Blog track this year?Iadh Ounishttps://www.blogger.com/profile/05740425172350940695noreply@blogger.comtag:blogger.com,1999:blog-6043705792807544709.post-87668957980742747802009-04-29T14:49:00.000+01:002009-04-29T14:49:00.000+01:00The new tasks sound very interesting. I don't com...The new tasks sound very interesting. I don't completely understand the evaluation plan for integration of facets with relevance. All of the proposed facets are binary valued. Will the query specify a facet + value a searcher might be interested in? Or just a facet? From the example, it looks like the latter. In that case, will the systems produce two ranked lists for each query -- one for facet value A and one for value B with the expectation that the two lists will be disjoint?Jonhttps://www.blogger.com/profile/14308358891592822280noreply@blogger.com