<meta http-equiv="content-type" content="text/html; charset=utf-8"><span class="Apple-style-span" style="border-collapse: collapse; font-family: arial, sans-serif; font-size: 15px; ">Reconcile is great. Thanks for the authors sharing. It should be a nice platform for researchers who are fresh to coreference resolution.</span><br>
<br><div>Best Wishes;</div><div>Lang Jun</div><div><br></div><div><div class="gmail_quote">2011/7/19 Jason Eisner <span dir="ltr"><<a href="mailto:jason@cs.jhu.edu">jason@cs.jhu.edu</a>></span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Reconcile was released last year as an common platform for coref, with up-to-date methods and good performance out of the box. <a href="http://www.cs.utah.edu/nlp/reconcile/" target="_blank">http://www.cs.utah.edu/nlp/reconcile/</a><br>
<br><div style="margin-left:40px">
"Reconcile is an automatic coreference resolution system that was
developed to provide a stable test-bed for researchers to implement new
ideas quickly and reliably.
It achieves roughly state of the art performance on many of the most
common coreference resolution test sets, such as MUC-6, MUC-7, and ACE.
Reconcile comes ready out of the box to train and test on these common
data sets (though the data sets are not provided) as well as the
ability to run on unlabeled texts.
Reconcile utilizes supervised machine learning classifiers from the
Weka toolkit, as well as other language processing tools such as the
Berkeley Parser and Stanford Named Entity Recognition system.
The source language is Java, and it is freely available under the GPL."<br></div><br><div class="gmail_quote"><div class="im">On Mon, Jul 18, 2011 at 1:24 PM, Leon Derczynski <span dir="ltr"><<a href="mailto:leon@dcs.shef.ac.uk" target="_blank">leon@dcs.shef.ac.uk</a>></span> wrote:<br>
</div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">Hi,<br>
<br>
What off-the-shelf coreference resolution packages would you recommend? So far I have Arkref, Stanford coref and BART working, and all seem to produce unsatisfactory results too often to be useful in practice. Is this characteristic of the state of the art?<br>
<br>
The text that I am trying to process is plaintext English newswire, and the entity types that I am most interested in resolving correctly are people and organisations. However currently at least one major actor per document appears to be incorrectly conflated with another entity; the president of the USA with an aircraft carrier, or "sanctions" with a country. Any tips or links to downlaodable systems would be greatly appreciated.<br>
<br></div>
All the best,<br>
<br>
<br>
Leon<br>
<br>
<br>
<br>
-- <br>
Leon R A Derczynski<br>
NLP Research Group<br>
<br>
Department of Computer Science<br>
University of Sheffield<br>
Regent Court, 211 Portobello<br>
Sheffield S1 4DP, UK<br>
<br>
<a href="tel:%2B44%20114%2022%2021931" value="+441142221931" target="_blank">+44 114 22 21931</a><br>
<a href="http://www.dcs.shef.ac.uk/%7Eleon/" target="_blank">http://www.dcs.shef.ac.uk/~<u></u>leon/</a><div class="im"><br>
<br>
______________________________<u></u>_________________<br>
UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/<u></u>corpora</a><br>
Corpora mailing list<br>
<a href="mailto:Corpora@uib.no" target="_blank">Corpora@uib.no</a><br>
<a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/<u></u>listinfo/corpora</a><br>
</div></blockquote></div><br>
<br>_______________________________________________<br>
UNSUBSCRIBE from this page: <a href="http://mailman.uib.no/options/corpora" target="_blank">http://mailman.uib.no/options/corpora</a><br>
Corpora mailing list<br>
<a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>
<a href="http://mailman.uib.no/listinfo/corpora" target="_blank">http://mailman.uib.no/listinfo/corpora</a><br>
<br></blockquote></div><br></div>