[Corpora-List] Detection of quotations and automatic attribution corpora

J. Nathan Matias natematias at gmail.com
Wed May 9 15:56:21 CEST 2012


Hi Chris,

I'm just spinning up a project in this area and would love to chat out of band with anyone who wants to collaborate.

René, the Reported Speech Tagger looks very cool. I look forward to trying it out!

A few more publications:

- The evri.com team uses a combination of "attribution verbs" quote-mark

searching, and entity extraction. "A large-scale system for annotating

and querying quotations in news feeds<http://dl.acm.org/citation.cfm?id=1863879.1863886>."

SEMSEARCH 2010

- Here's the Europe Media Monitoring Paper: Opinion Mining on Newspaper

Quotations<http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5285040>

- There was also a big CMU initiative in this area recently. Here's

their technical report (2010): "Visualizing Topical Quotations Over Time

to Understand News Discourse<http://www.cs.cmu.edu/~nschneid/ravine-tr.pdf>

"

Regards,

-- J. Nathan Matias <http://natematias.com/portfolio/> : MIT Media Lab
: (001)857 277 3397 : @natematias <http://twitter.com/natematias> :
protocol<http://protocol.by/natematias>

On Mon, Apr 23, 2012 at 3:52 PM, René Witte <witte at semanticsoftware.info>wrote:


> Hello,
>
> > Does anyone know of any related corpora or articles on
> > the automatic detection of quotations and the attribution of authors to
> > quotations (for any domain)?
>
> Have a look at our Reported Speech Tagger components:
> http://www.semanticsoftware.info/reported-speech-tagger
>
> And the corresponding publication:
> Ralf Krestel, Sabine Bergler, and René Witte:
> Minding the Source: Automatic Tagging of Reported Speech
> in Newspaper Articles.
> Proceedings of the Sixth International Language Resources and
> Evaluation
> Conference (LREC 2008), Marrakech, Morocco, May 28–30, 2008.
> http://rene-witte.net/reported-speech-tagging
>
> Cheers, René
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3237 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120509/9cffe1fc/attachment.txt>



More information about the Corpora mailing list