Revision: 17328
http://sourceforge.net/p/gate/code/17328
Author: dgmaynard
Date: 2014-02-17 17:24:45 +0000 (Mon, 17 Feb 2014)
Log Message:
-----------
Kaboom! Twitie app now has its own special version of the ANNIE grammar and the
hashtag tokeniser
Modified Paths:
--------------
gate/trunk/plugins/Twitter/resources/twitie-en.xgapp
Modified: gate/trunk/plugins/Twitter/resources/twitie-en.xgapp
===================================================================
--- gate/trunk/plugins/Twitter/resources/twitie-en.xgapp 2014-02-17
17:22:25 UTC (rev 17327)
+++ gate/trunk/plugins/Twitter/resources/twitie-en.xgapp 2014-02-17
17:24:45 UTC (rev 17328)
@@ -2,20 +2,62 @@
<urlList class="gate.util.persistence.CollectionPersistence">
<localList>
<gate.util.persistence.PersistenceManager-URLHolder>
- <urlString>$gatehome$plugins/Tools/</urlString>
+
<urlString>$relpath$../../../../gate-extras/plugins/CorpusQA2/</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
<gate.util.persistence.PersistenceManager-URLHolder>
- <urlString>$gatehome$plugins/ANNIE/</urlString>
+ <urlString>$relpath$../../ANNIE/</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
<gate.util.persistence.PersistenceManager-URLHolder>
- <urlString>$gatehome$plugins/Language_Identification/</urlString>
+ <urlString>$relpath$../../Twitter/</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
<gate.util.persistence.PersistenceManager-URLHolder>
- <urlString>$gatehome$plugins/Tagger_Stanford</urlString>
+ <urlString>$relpath$../../Tagger_Stanford/</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
<gate.util.persistence.PersistenceManager-URLHolder>
- <urlString>$relpath$..</urlString>
+ <urlString>$relpath$../../Tools/</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Language_Identification/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Tagger_DateNormalizer/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Groovy/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/arcomem/plugins/Arcomem/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../TermRaider/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/arcomem/plugins/AppDoc/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Tagger_Boilerpipe/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Tagger_NP_Chunking/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../JAPE_Plus/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Alignment/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$../../Tagger_Framework/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/arcomem/plugins/StringAnnotation/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/gate-twitter/applications/plugins/Normaliser_Twitter/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/arcomem/plugins/HashtagTokenizer/</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
</localList>
<collectionType>java.util.ArrayList</collectionType>
</urlList>
@@ -29,7 +71,37 @@
<pr class="gate.util.persistence.PRPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>setsToKeep</string>
+ <gate.util.persistence.CollectionPersistence>
+ <localList>
+ <string>Key</string>
+ </localList>
+ <collectionType>java.util.ArrayList</collectionType>
+ </gate.util.persistence.CollectionPersistence>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>annotationTypes</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>setsToRemove</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>keepOriginalMarkupsAS</string>
+ <boolean>true</boolean>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.annotdelete.AnnotationDeletePR</resourceType>
<resourceName>Document Reset</resourceName>
@@ -64,6 +136,10 @@
<null/>
</entry>
<entry>
+ <string>copyAnnotations</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
<string>tagASName</string>
<string>Original markups</string>
</entry>
@@ -78,10 +154,6 @@
</gate.util.persistence.CollectionPersistence>
</entry>
<entry>
- <string>copyAnnotations</string>
- <boolean>true</boolean>
- </entry>
- <entry>
<string>inputASName</string>
<string>Original markups</string>
</entry>
@@ -112,6 +184,22 @@
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
<localMap>
<entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>languageFeatureName</string>
+ <string>lang</string>
+ </entry>
+ <entry>
+ <string>annotationSetName</string>
+ <null/>
+ </entry>
+ <entry>
<string>annotationType</string>
<string>Tweet</string>
</entry>
@@ -143,7 +231,28 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>wholeWordsOnly</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>longestMatchOnly</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>annotationSetName</string>
+ <null/>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.gazetteer.DefaultGazetteer</resourceType>
<resourceName>Emoticons Gazetteer</resourceName>
@@ -161,13 +270,13 @@
<boolean>true</boolean>
</entry>
<entry>
+ <string>gazetteerFeatureSeparator</string>
+ <string> </string>
+ </entry>
+ <entry>
<string>encoding</string>
<string>UTF-8</string>
</entry>
- <entry>
- <string>gazetteerFeatureSeparator</string>
- <string> </string>
- </entry>
</localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
@@ -183,7 +292,20 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>annotationSetName</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.tokeniser.DefaultTokeniser</resourceType>
<resourceName>Twitter Tokenizer (EN)</resourceName>
@@ -191,16 +313,71 @@
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
<localMap>
<entry>
+ <string>encoding</string>
+ <string>UTF-8</string>
+ </entry>
+ <entry>
+ <string>tokeniserRulesURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../ANNIE/resources/tokeniser/DefaultTokeniser.rules</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ <entry>
<string>transducerGrammarURL</string>
<gate.util.persistence.PersistenceManager-URLHolder>
<urlString>$relpath$tokeniser/twitter+English.jape</urlString>
</gate.util.persistence.PersistenceManager-URLHolder>
</entry>
+ </localMap>
+ </initParams>
+ <features class="gate.util.persistence.MapPersistence">
+ <mapType>gate.util.SimpleFeatureMapImpl</mapType>
+ <localMap/>
+ </features>
+ </pr>
+ </gate.util.persistence.AnalyserRunningStrategyPersistence>
+ <gate.util.persistence.AnalyserRunningStrategyPersistence>
+ <runMode>1</runMode>
+ <featureName></featureName>
+ <featureValue></featureValue>
+ <pr class="gate.util.persistence.LanguageAnalyserPersistence">
+ <runtimeParams class="gate.util.persistence.MapPersistence">
+ <mapType>gate.util.SimpleFeatureMapImpl</mapType>
+ <localMap>
<entry>
- <string>encoding</string>
- <string>UTF-8</string>
+ <string>outputASName</string>
+ <null/>
</entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>debug</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>inputASName</string>
+ <null/>
+ </entry>
</localMap>
+ </runtimeParams>
+ <resourceType>gate.twitter.HashtagTokenizer</resourceType>
+ <resourceName>Hashtag Tokenizer</resourceName>
+ <initParams class="gate.util.persistence.MapPersistence">
+ <mapType>gate.util.SimpleFeatureMapImpl</mapType>
+ <localMap>
+ <entry>
+ <string>gazetteerURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../../../gate-extras/arcomem/plugins/HashtagTokenizer/resources/gazetteer/lists.def</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -215,13 +392,53 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>wholeWordsOnly</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>longestMatchOnly</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>annotationSetName</string>
+ <null/>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.gazetteer.DefaultGazetteer</resourceType>
<resourceName>ANNIE Gazetteer</resourceName>
<initParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap />
+ <localMap>
+ <entry>
+ <string>listsURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../ANNIE/resources/gazetteer/lists.def</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ <entry>
+ <string>caseSensitive</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>gazetteerFeatureSeparator</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>encoding</string>
+ <string>UTF-8</string>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -236,13 +453,47 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>outputASName</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>inputASName</string>
+ <null/>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.splitter.SentenceSplitter</resourceType>
<resourceName>ANNIE Sentence Splitter</resourceName>
<initParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap />
+ <localMap>
+ <entry>
+ <string>encoding</string>
+ <string>UTF-8</string>
+ </entry>
+ <entry>
+ <string>gazetteerListsURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../ANNIE/resources/sentenceSplitter/gazetteer/lists.def</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ <entry>
+ <string>transducerURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../ANNIE/resources/sentenceSplitter/grammar/main.jape</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -255,13 +506,59 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>normTextFeature</string>
+ <string>string</string>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>maxDistance</string>
+ <string>2.0</string>
+ </entry>
+ <entry>
+ <string>inputASName</string>
+ <string></string>
+ </entry>
+ <entry>
+ <string>outputASName</string>
+ <string></string>
+ </entry>
+ <entry>
+ <string>initialTextFeature</string>
+ <string>string</string>
+ </entry>
+ <entry>
+ <string>origTextFeature</string>
+ <string>origString</string>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.twitter.Normaliser</resourceType>
<resourceName>Tweet Normaliser (EN)</resourceName>
<initParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>dictURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$normaliser/english.jaspell</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ <entry>
+ <string>orthURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$normaliser/orth.en.csv</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -276,13 +573,61 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>outputAnnotationType</string>
+ <string>Token</string>
+ </entry>
+ <entry>
+ <string>inputASName</string>
+ <string></string>
+ </entry>
+ <entry>
+ <string>failOnMissingInputAnnotations</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>outputASName</string>
+ <string></string>
+ </entry>
+ <entry>
+ <string>useExistingTags</string>
+ <boolean>true</boolean>
+ </entry>
+ <entry>
+ <string>baseSentenceAnnotationType</string>
+ <string>Sentence</string>
+ </entry>
+ <entry>
+ <string>baseTokenAnnotationType</string>
+ <string>Token</string>
+ </entry>
+ <entry>
+ <string>posTagAllTokens</string>
+ <boolean>true</boolean>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.twitter.pos.POSTaggerEN</resourceType>
<resourceName>Tweet PoS Tagger (EN)</resourceName>
<initParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>modelFile</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+ <urlString>$relpath$pos/gate-EN-twitter.model</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -297,13 +642,49 @@
<pr class="gate.util.persistence.LanguageAnalyserPersistence">
<runtimeParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap/>
+ <localMap>
+ <entry>
+ <string>outputASName</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>document</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>corpus</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>inputASName</string>
+ <null/>
+ </entry>
+ </localMap>
</runtimeParams>
<resourceType>gate.creole.ANNIETransducer</resourceType>
- <resourceName>ANNIE NE Transducer</resourceName>
+ <resourceName>ANNIE NE Twitter Transducer</resourceName>
<initParams class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
- <localMap />
+ <localMap>
+ <entry>
+ <string>encoding</string>
+ <string>UTF-8</string>
+ </entry>
+ <entry>
+ <string>grammarURL</string>
+ <gate.util.persistence.PersistenceManager-URLHolder>
+
<urlString>$relpath$../../ANNIE/resources/NE/main-twitter.jape</urlString>
+ </gate.util.persistence.PersistenceManager-URLHolder>
+ </entry>
+ <entry>
+ <string>annotationAccessors</string>
+ <null/>
+ </entry>
+ <entry>
+ <string>operators</string>
+ <null/>
+ </entry>
+ </localMap>
</initParams>
<features class="gate.util.persistence.MapPersistence">
<mapType>gate.util.SimpleFeatureMapImpl</mapType>
@@ -326,6 +707,7 @@
<gate.util.persistence.LanguageAnalyserPersistence
reference="../../../strategiesList/localList/gate.util.persistence.AnalyserRunningStrategyPersistence[8]/pr"/>
<gate.util.persistence.LanguageAnalyserPersistence
reference="../../../strategiesList/localList/gate.util.persistence.AnalyserRunningStrategyPersistence[9]/pr"/>
<gate.util.persistence.LanguageAnalyserPersistence
reference="../../../strategiesList/localList/gate.util.persistence.AnalyserRunningStrategyPersistence[10]/pr"/>
+ <gate.util.persistence.LanguageAnalyserPersistence
reference="../../../strategiesList/localList/gate.util.persistence.AnalyserRunningStrategyPersistence[11]/pr"/>
</localList>
<collectionType>java.util.ArrayList</collectionType>
</prList>
@@ -351,4 +733,4 @@
</localMap>
</features>
</application>
-</gate.util.persistence.GateApplication>
+</gate.util.persistence.GateApplication>
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
Managing the Performance of Cloud-Based Applications
Take advantage of what the Cloud has to offer - Avoid Common Pitfalls.
Read the Whitepaper.
http://pubads.g.doubleclick.net/gampad/clk?id=121054471&iu=/4140/ostg.clktrk
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs