tag:blogger.com,1999:blog-19803222.post115411988293295128..comments2024-03-18T01:45:45.724-06:00Comments on natural language processing blog: Loss versus Conditional Probabilityhalhttp://www.blogger.com/profile/02162908373916390369noreply@blogger.comBlogger5125tag:blogger.com,1999:blog-19803222.post-58812024337964710822009-05-12T11:16:00.000-06:002009-05-12T11:16:00.000-06:00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-1154788423411320182006-08-05T08:33:00.000-06:002006-08-05T08:33:00.000-06:00Kevin -- I've wanted to do just that for parsing, ...Kevin -- I've wanted to do just that for parsing, perhaps with a summarization, EDT and MT system, but the overhead for trying such an experiment is daunting (not to mention the issue of <A HREF="http://nlpers.blogspot.com/2006/03/is-x-useful-for-y.html" REL="nofollow">engineering around syntax</A>). Incidentally, <A HREF="http://www.isi.edu/~fraser/" REL="nofollow">Alex Fraser</A> has done just this for <A HREF="http://www.isi.edu/~fraser/pubs/fraser_tr616_alignqual.pdf" REL="nofollow">alignments</A>.<BR/><BR/>Bob -- I think I agree with Chris too, to a large degree. I'll have to read the Culotta and McCallum paper...in general I'm not a huge fan of these encodings for sequence segmentation (preferring direct segmentation models), but the paper sounds interesting.halhttps://www.blogger.com/profile/02162908373916390369noreply@blogger.comtag:blogger.com,1999:blog-19803222.post-1154330249260634832006-07-31T01:17:00.000-06:002006-07-31T01:17:00.000-06:00I totally agree with Chris on this. We're using t...I totally agree with Chris on this. <BR/><BR/>We're using the confidence scores as counts in a corpus that we use for data mining and information retrieval of genes by name.<BR/><BR/>It's easy to convert a forward-backward lattice of tag probabilities to those of chunks. With a BIO-encoding of chunks as tags, check out Culotta and McCallum's <A HREF="http://www.nytimes.com/2006/07/31/business/31men.html" REL="nofollow"> Confidence Estimation for Information Extraction</A>, somehow only accepted as a poster.<BR/><BR/>We used a Begin-Middle-End-Whole encoding of chunkings as taggings in LingPipe, and it makes it a whole lot easier to do extraction. It pulls out n-best chunks (or n-best whole analyses) with conditional probability scores at 330K/second.<BR/>We just <A HREF="http://www.alias-i.com/blog/?p=21" REL="nofollow">ran it over all of MEDLINE</A>. <BR/><BR/>For what it's worth, pulling back most likely sequences vs. most likely tags is not always the same for POS, but the scores are always very close in my experience. We have tutorials on POS with confidence and entity extraction with confidence.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-1154219959826981182006-07-29T18:39:00.000-06:002006-07-29T18:39:00.000-06:00Hi Hal,Thanks for this thoughtful post. It would b...Hi Hal,<BR/><BR/>Thanks for this thoughtful post. It would be great if you mention some interesting papers which you have seen in the conference in a special post. That would be great for those who could not make it to the conference.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-19803222.post-1154130321071561942006-07-28T17:45:00.000-06:002006-07-28T17:45:00.000-06:00This is a very thought-provoking post. I was at th...This is a very thought-provoking post. I was at the talk too but didn't make this connection. It's interesting that the critical question "What do we optimize?" isn't clear all the time in our problems. It'll be really interesting if someone could empirically try the various optimization criteria for chunking/tagging and see how that REALLY affects the later stages in the pipeline. (Of course, then we nead some goodness measure for the final stage too...)Kevin Duhhttps://www.blogger.com/profile/07407894290644783502noreply@blogger.com