<feed xmlns='http://www.w3.org/2005/Atom'>
<title>gf-core.git/treebanks/PennTreebank/training.hs, branch master</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<id>https://git.adelon.net/gf-core.git/atom?h=master</id>
<link rel='self' href='https://git.adelon.net/gf-core.git/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git.adelon.net/gf-core.git/'/>
<updated>2013-11-06T10:21:46+00:00</updated>
<entry>
<title>the content of ParseEngAbs3.probs is now merged with ParseEngAbs.probs. The later is now retrained. Once the grammar is compiled with the .probs file now it doesn't need anything more to do robust parsing. The robustness itself is controlled by the flags 'heuristic_search_factor', 'meta_prob' and 'meta_token_prob' in ParseEngAbs.gf</title>
<updated>2013-11-06T10:21:46+00:00</updated>
<author>
<name>kr.angelov</name>
<email>kr.angelov@gmail.com</email>
</author>
<published>2013-11-06T10:21:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.adelon.net/gf-core.git/commit/?id=2483dc772897eb0909664f1a88cc7f8ec50ebd5b'/>
<id>urn:sha1:2483dc772897eb0909664f1a88cc7f8ec50ebd5b</id>
<content type='text'>
</content>
</entry>
<entry>
<title>move examples/PennTreebank to /treebanks/PennTreebank</title>
<updated>2012-10-01T08:52:54+00:00</updated>
<author>
<name>kr.angelov</name>
<email>kr.angelov@gmail.com</email>
</author>
<published>2012-10-01T08:52:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.adelon.net/gf-core.git/commit/?id=6e3503bb7b6c9aac12711477b8a474ce41c1cd7a'/>
<id>urn:sha1:6e3503bb7b6c9aac12711477b8a474ce41c1cd7a</id>
<content type='text'>
</content>
</entry>
</feed>
