tag:blogger.com,1999:blog-19803222.post116120646465890215..comments2024-03-18T01:45:45.724-06:00Comments on natural language processing blog: The Shared Task Effecthalhttp://www.blogger.com/profile/02162908373916390369noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-19803222.post-4612822981141960922009-05-12T11:11:00.000-06:002009-05-12T11:11:00.000-06:00酒店經紀PRETTY GIRL 台北酒店經紀人 ,禮服店 酒店兼差PRETTY GIRL酒店公關 酒...酒店經紀PRETTY GIRL <A HREF="http://www.taipeilady.com/" REL="nofollow" TITLE="台北酒店經紀人">台北酒店經紀人</A> ,<A HREF="http://tw.myblog.yahoo.com/jw!qZ9n..6QEhhc0LkItOBm/" REL="nofollow" TITLE="禮服店">禮服店</A> 酒店兼差PRETTY GIRL<A HREF="http://www.mashow.org/" REL="nofollow" TITLE="酒店公關">酒店公關</A> 酒店小姐 彩色爆米花<A HREF="http://blog.xuite.net/jkl338801/blog/" REL="nofollow" TITLE="酒店兼職">酒店兼職</A>,酒店工作 彩色爆米花<A HREF="http://tw.myblog.yahoo.com/jw!BIBoU5SeBRs21nb_ajFpncbTqXds" REL="nofollow" TITLE="酒店經紀">酒店經紀</A>, <A HREF="http://mypaper.pchome.com.tw/news/thomsan/3/1310065116/20080905040949/" REL="nofollow" TITLE="酒店上班">酒店上班</A>,酒店工作 PRETTY GIRL<A HREF="http://tw.myblog.yahoo.com/jw!rybqykeeER6TH3AKz1HQ5grm/" REL="nofollow" TITLE="酒店喝酒">酒店喝酒</A>酒店上班 彩色爆米花<A HREF="http://mypaper.pchome.com.tw/news/jkl338801/" REL="nofollow" TITLE="台北酒店">台北酒店</A>酒店小姐 PRETTY GIRL<A HREF="http://www.mashow.org/" REL="nofollow" TITLE="酒店上班">酒店上班</A>酒店打工PRETTY GIRL<A HREF="http://www.tpangel.com/" REL="nofollow" TITLE="酒店打工">酒店打工</A>酒店經紀 彩色爆米花Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-52592441920956396042007-01-16T07:03:00.000-07:002007-01-16T07:03:00.000-07:00Another serious drawback of shared tasks is that m...Another serious drawback of shared tasks is that many people see them not as research, a share opportuntity to learn, but as a competitive event. This leads to behavious that increases the idiosyncacies of sumitted systems (adding ad-hoc hacks to "rank" better, to improve the score) at the cost of control. This is why often, no true learning experience is the result.<br /><br />--<br />Jochen L Leidner<br />Linguit Ltd. (www.linguit.com)Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-1161356296716321372006-10-20T08:58:00.000-06:002006-10-20T08:58:00.000-06:00Nice post Hal. Having participated in a couple sha...Nice post Hal. Having participated in a couple shared tasks in the past I have often thought about this. The idea of fixing either the learning or features and varying the other is a reasonable thought, but I am not sure how feasible it is. In my opinion, the most interesting part of these shared tasks is <I>representation</I>. For example, at last years CoNLL task on dependency parsing, people used: spanning tree, stacked-based, CFG, plus some other representations of the problem. In this case, it is not always true that you can fix the learning or feature-set since each representation of the problem may be incompatible with a particular choice. For instance, lets say we want the learning to be discriminative max-likelihood (CRF). For the spanning tree parsing methods it is not clear to me that this can be done (i.e., I know how to do inference and normalization, but I do not know how to compute feature expectations. Just curious, does anyone?). I think leaving as many dimensions free as possible is beneficial. After the shared-task, people can then go and create studies comparing various techniques in a more controlled setting. The only dimension I think is important to be strict about is resources, especially now that people are finding good ways to use unlabeled data. In this case one can have two-tracks "open" and "closed" to allow people to experiment.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-1161283698443054552006-10-19T12:48:00.000-06:002006-10-19T12:48:00.000-06:00I totally agree about the pros and cons, but share...I totally agree about the pros and cons, but shared tasks mean me a bit different. They are the places where the tools don't matter, only your performance. Someone tune on features others on learning, it isn't a problem (to my personal view). It could highlight new topics which worth the time to deal with (at least when you built an application) e.g. a simple system with a postprocessing step (containing few expert rules) can beat the most sophisticated algorithms. <BR/>Obviously it is interesting only if the goal is to solve problems, not just to release theories.Anonymousnoreply@blogger.com