Comments for Michael Fagan's blog http://faganm.com/blog Thu, 28 Jul 2011 11:21:17 +0000 hourly 1 http://wordpress.org/?v=3.3.1 Comment on Entity Extraction APIs, once again by Comparing NLP APIs for Entity Extraction | Michael Fagan's blog http://faganm.com/blog/2011/07/26/1014/#comment-41179 Comparing NLP APIs for Entity Extraction | Michael Fagan's blog Thu, 28 Jul 2011 11:21:17 +0000 http://faganm.com/blog/2010/01/19/1014/#comment-41179 [...] Update: a number have people have pointed out some small errors and some additional APIs that I should look at. See my half-hearted followup: Entity Extraction APIs, once again. [...] [...] Update: a number have people have pointed out some small errors and some additional APIs that I should look at. See my half-hearted followup: Entity Extraction APIs, once again. [...]

]]> Comment on Comparing NLP APIs for Entity Extraction by John Lehmann http://faganm.com/blog/2010/01/02/1009/#comment-40577 John Lehmann Tue, 04 Jan 2011 00:02:55 +0000 http://faganm.com/blog/2010/01/02/1009/#comment-40577 <p>This was a great article — one of the few comparisons of its kind and still relevant a year later.</p> <p>A Quora post which I have linked to this blogpost is:<br /> <a href='http://www.quora.com/What-is-the-best-text-analytics-API' rel='nofollow'>http://www.quora.com/What-is-the-best-text-analytics-API</a></p> <p>I’d also like to add Extractiv to the list, which hit the scene in late 2010. Extractiv’s novelty is that it combines NLP with web crawling to provide an integrated solution for transforming the open web into structured semantic metadata. It also provides a REST-based On-Demand API for processing your own documents, like the services mentioned above. Metadata output includes over 150 entity types, synonyms (coreference chains), semantic links (linked entities), and relations (facts and events), and output formats such as JSON and RDF. More including a live demo is at <a href='http://www.extractiv.com' rel='nofollow'>http://www.extractiv.com</a>. </p> This was a great article — one of the few comparisons of its kind and still relevant a year later.

A Quora post which I have linked to this blogpost is:
http://www.quora.com/What-is-the-best-text-analytics-API

I’d also like to add Extractiv to the list, which hit the scene in late 2010. Extractiv’s novelty is that it combines NLP with web crawling to provide an integrated solution for transforming the open web into structured semantic metadata. It also provides a REST-based On-Demand API for processing your own documents, like the services mentioned above. Metadata output includes over 150 entity types, synonyms (coreference chains), semantic links (linked entities), and relations (facts and events), and output formats such as JSON and RDF. More including a live demo is at http://www.extractiv.com.

]]> Comment on Toronto Election Polls by mfagan http://faganm.com/blog/2010/09/20/1037/#comment-40368 mfagan Thu, 23 Sep 2010 02:44:05 +0000 http://faganm.com/blog/2010/09/20/1037/#comment-40368 <p>that’s quite true, although the wikipedia page didn’t include the margins of error, and I didn’t want to track that down. Plus I would have struggled more to figure out how to creat the plots ;-)</p> <p>feel free to try it yourself. </p> that’s quite true, although the wikipedia page didn’t include the margins of error, and I didn’t want to track that down. Plus I would have struggled more to figure out how to creat the plots ;-)

feel free to try it yourself.

]]> Comment on Toronto Election Polls by Anon http://faganm.com/blog/2010/09/20/1037/#comment-40367 Anon Tue, 21 Sep 2010 12:20:20 +0000 http://faganm.com/blog/2010/09/20/1037/#comment-40367 <p>Don’t plot poll results by directly interpolating them. They don’t represent exact numbers, they (together with their margins of error) represent an estimate where the actual numbers are, so a graph like this is more appropriate: <a href='http://en.wikipedia.org/wiki/File:2008FederalElectionPolls.png' rel='nofollow'>http://en.wikipedia.org/wiki/File:2008FederalElectionPolls.png</a> </p> Don’t plot poll results by directly interpolating them. They don’t represent exact numbers, they (together with their margins of error) represent an estimate where the actual numbers are, so a graph like this is more appropriate: http://en.wikipedia.org/wiki/File:2008FederalElectionPolls.png

]]> Comment on Technical Ramblings » Blog Archive » MetaCarta Acquired by Nokia by mfagan http://faganm.com/blog/2010/04/09/1022/#comment-39744 mfagan Tue, 13 Apr 2010 14:44:27 +0000 http://faganm.com/blog/2010/04/09/1022/#comment-39744 <p>I meant the ones listed here <a href='http://developers.metacarta.com/api/' rel='nofollow'>http://developers.metacarta.com/api/</a> … which I’m guessing are the ones described by that page? </p> I meant the ones listed here http://developers.metacarta.com/api/ … which I’m guessing are the ones described by that page?

]]> Comment on Technical Ramblings » Blog Archive » MetaCarta Acquired by Nokia by Christopher Schmidt http://faganm.com/blog/2010/04/09/1022/#comment-39741 Christopher Schmidt Fri, 09 Apr 2010 15:22:57 +0000 http://faganm.com/blog/2010/04/09/1022/#comment-39741 <p>Which APIs? If you’re talking about OnDemand, I recommend taking a look at <a href='http://ondemand.metacarta.com/' rel='nofollow'>http://ondemand.metacarta.com/</a> . </p> Which APIs? If you’re talking about OnDemand, I recommend taking a look at http://ondemand.metacarta.com/ .

]]> Comment on Some notes on Map Kibera mapping – Mikel Maron by mfagan http://faganm.com/blog/2010/01/20/1012/#comment-38709 mfagan Thu, 28 Jan 2010 18:37:50 +0000 http://faganm.com/blog/2010/01/16/1012/#comment-38709 <p>Hey Paul, you’re alive! :-p</p> <p>I already read Richard’s blog but haven’t met him yet, but I will on Wednesday as he’s coordinating a meetup: <a href='http://www.meetup.com/Waterloo-OSM/calendar/12427012/' rel='nofollow'>http://www.meetup.com/Waterloo-OSM/calendar/12427012/</a></p> <p>You’ll have to let me know what’s going on with you so we can meet up. </p> Hey Paul, you’re alive! :-p

I already read Richard’s blog but haven’t met him yet, but I will on Wednesday as he’s coordinating a meetup: http://www.meetup.com/Waterloo-OSM/calendar/12427012/

You’ll have to let me know what’s going on with you so we can meet up.

]]> Comment on Some notes on Map Kibera mapping – Mikel Maron by Paul N http://faganm.com/blog/2010/01/20/1012/#comment-38682 Paul N Thu, 28 Jan 2010 07:05:06 +0000 http://faganm.com/blog/2010/01/16/1012/#comment-38682 <p>I am going to make this comment as spammy as possible.</p> <p>Hey yo you should check out Richard Weait’s blog and become friends with him: <a href='http://www.weait.com' rel='nofollow'>http://www.weait.com</a> . He’s a cool guy and even more into this OpenStreetMap stuff than you are. Given that I have TOP SECRET KNOWLEDGE that you are in Waterloo at the moment, I am sure he will want to be your friend too!</p> <p>- Paul </p> I am going to make this comment as spammy as possible.

Hey yo you should check out Richard Weait’s blog and become friends with him: http://www.weait.com . He’s a cool guy and even more into this OpenStreetMap stuff than you are. Given that I have TOP SECRET KNOWLEDGE that you are in Waterloo at the moment, I am sure he will want to be your friend too!

- Paul

]]> Comment on Comparing NLP APIs for Entity Extraction by Vasco Pedro http://faganm.com/blog/2010/01/02/1009/#comment-38277 Vasco Pedro Tue, 19 Jan 2010 23:30:20 +0000 http://faganm.com/blog/2010/01/02/1009/#comment-38277 <p>Excellent work in comparing all the API’s. It was about time someone did and I think that your work will lead to more detailed comparisons, which is great. I look forward to read the update. I believe that if you keep up with this, buy running and refining the test sets, you could have a reference page that would be tremendously beneficial. Goo luck with you project. </p> Excellent work in comparing all the API’s. It was about time someone did and I think that your work will lead to more detailed comparisons, which is great. I look forward to read the update. I believe that if you keep up with this, buy running and refining the test sets, you could have a reference page that would be tremendously beneficial. Goo luck with you project.

]]> Comment on The Loudness Wars (and leaf blowers) by mfagan http://faganm.com/blog/2010/01/18/1013/#comment-38276 mfagan Tue, 19 Jan 2010 23:01:39 +0000 http://faganm.com/blog/2010/01/16/1013/#comment-38276 <p>Neat, thanks for the info and link to the video. </p> Neat, thanks for the info and link to the video.

]]>