merge master in

Author: Grace Muzny

CONTRIBUTING.md

@@ -8,9 +8,13 @@ However, Stanford CoreNLP is copyright by Stanford. (Technically, by The Board o
 In order for us to continue to be able to dual-license Stanford CoreNLP, we need to make sure that contributions from others do not restrict Stanford from separately licensing the code.
 
 Therefore, we can accept contributions on any of the following terms:
+
  * If your contribution is a bug fix of 6 lines or less of new code, we will accept it on the basis that both you and us regard the contribution as de minimis, and not requiring further hassle.
  * You can declare that the contribution is in the public domain (in your commit message or pull request).
  * You can make your contribution available under a non-restrictive open source license, such as the Revised (or 3-clause) BSD license, with appropriate licensing information included with the submitted code.
- * You can sign and return to us a contributor license agreement (CLA), explicitly licensing us to be able to use the code. You can find these agreements at http://nlp.stanford.edu/software/CLA/ . You can send them to us or contact us at: [email protected] .
+ * You can sign and return to us a contributor license agreement (CLA), explicitly licensing us to be able to use the code.
+   There is a [Contributor License Agreement for Individuals](http://nlp.stanford.edu/software/CLA/individual.html) and
+   a [Contributor License Agreement for Corporations](http://nlp.stanford.edu/software/CLA/corporate.html).
+   You can send them to us or contact us at: [email protected] .
 
 You should do development against our master branch. The project's source code is in utf-8 character encoding. You should make sure that all unit tests still pass. (In general, you will not be able to run our integration tests, since they rely on resources in our filesystem.)

LICENSE.txt

@@ -5,12 +5,24 @@ Stanford CoreNLP provides a set of natural language analysis tools written in Ja
 
 The Stanford CoreNLP code is written in Java and licensed under the GNU General Public License (v3 or later). Note that this is the full GPL, which allows many free uses, but not its use in proprietary software that you distribute to others.
 
+#### How To Compile (with ant)
+
+1. cd CoreNLP ; ant
+
+#### How To Create A Jar 
+
+1. compile the code
+2. cd CoreNLP/classes ; jar -cf ../stanford-corenlp.jar edu
+
 You can find releases of Stanford CoreNLP on [Maven Central](http://search.maven.org/#browse%7C11864822).
 
 You can find more explanation and documentation on [the Stanford CoreNLP homepage](http://nlp.stanford.edu/software/corenlp.shtml#Demo).
 
 The most recent models associated with the code in the HEAD of this repository can be found [here](http://nlp.stanford.edu/software/stanford-corenlp-models-current.jar).
 
+Some of the larger (English) models -- like the shift-reduce parser and WikiDict -- are not distributed with our default models jar. 
+The most recent version of these models can be found [here](http://nlp.stanford.edu/software/stanford-english-corenlp-models-current.jar).
+
 For information about making contributions to Stanford CoreNLP, see the file [CONTRIBUTING.md](CONTRIBUTING.md).
 
 Questions about CoreNLP can either be posted on StackOverflow with the tag [stanford-nlp](http://stackoverflow.com/questions/tagged/stanford-nlp), 

README.md

@@ -11,7 +11,7 @@ sourceCompatibility = 1.8
 targetCompatibility = 1.8
 compileJava.options.encoding = 'UTF-8'
 
-version = '3.4.1'
+version = '3.6.0'
 
 // Gradle application plugin
 mainClassName = "edu.stanford.nlp.pipeline.StanfordCoreNLP"

build.gradle

@@ -133,6 +133,11 @@
         <exclude name="**/*.java"/>
       </fileset>
     </copy>
+    <copy todir="${build.path}/edu/stanford/nlp/pipeline">
+      <fileset dir="${source.path}/edu/stanford/nlp/pipeline">
+        <exclude name="**/*.java"/>
+      </fileset>
+    </copy>
   </target>
 
   <target name="test" depends="classpath,compile"
@@ -173,7 +178,7 @@
   <target name="slowitest" depends="classpath,compile"
           description="Run really slow integration tests">
     <echo message="${ant.project.name}" />
-    <junit fork="yes" maxmemory="8g" printsummary="off" outputtoformatters="false" forkmode="perTest" haltonfailure="true">
+    <junit fork="yes" maxmemory="12g" printsummary="off" outputtoformatters="false" forkmode="perTest" haltonfailure="true">
       <classpath refid="classpath"/>
       <classpath path="${build.path}"/>
       <classpath path="${data.path}"/>
@@ -308,7 +313,7 @@
         <include name="commons-lang3-3.1.jar"/>
         <include name="xom-1.2.10.jar"/>
         <include name="joda-time.jar"/>
-        <include name="jollyday-0.4.7.jar"/>
+        <include name="jollyday-0.4.9.jar"/>
       </lib>
       <zipfileset prefix="WEB-INF/data"
                   file="/u/nlp/data/pos-tagger/distrib/english-left3words-distsim.tagger"/>
@@ -441,7 +446,7 @@
         <include name="xom-1.2.10.jar"/>
         <include name="xml-apis.jar"/>
         <include name="joda-time.jar"/>
-        <include name="jollyday-0.4.7.jar"/>
+        <include name="jollyday-0.4.9.jar"/>
       </lib>
       <!-- note for John: c:/Users/John Bauer/nlp/stanford-releases -->
       <lib dir="/u/nlp/data/StanfordCoreNLPModels">

build.xml

@@ -124,7 +124,7 @@ RB=target <... {/.*/}
 relabel target ADV
 
 % DT -> PRON (pronominal this/that/these/those)
-@NP <: (DT=target < /^[Tt]h(is|at|ose|ese)$/)
+@NP <: (DT=target < /^(?i:th(is|at|ose|ese))$/)
 
 relabel target PRON
 
@@ -133,6 +133,21 @@ DT=target < __
 
 relabel target DET
 
+% WDT -> PRON (pronominal that/which)
+@WHNP|NP <: (WDT=target < /^(?i:(that|which))$/)
+
+relabel target PRON
+
+% WDT->SCONJ (incorrectly tagged subordinating conjunctions)
+@SBAR < (WDT=target < /^(?i:(that|which))$/)
+
+relabel target SCONJ
+
+% WDT -> DET
+WDT=target <... {/.*/}
+
+relabel target DET
+
 % ------------------------------
 % 1 to 1 mappings
 %
@@ -227,11 +242,6 @@ UH=target <... {/.*/}
 
 relabel target INTJ
 
-% WDT -> DET
-WDT=target <... {/.*/}
-
-relabel target DET
-
 % WP -> PRON
 WP=target <... {/.*/}
 

data/edu/stanford/nlp/upos/ENUniversalPOS.tsurgeon

@@ -1,4 +1,4 @@
-Stanford Classifier v3.5.2 - 2015-04-20
+Stanford Classifier v3.6.0 - 2015-12-09
 -------------------------------------------------
 
 Copyright (c) 2003-2012 The Board of Trustees of 
@@ -24,7 +24,7 @@ QUICKSTART
 COMMAND LINE INTERFACE
 To classify the included example dataset cheeseDisease (in the examples directory), type the following at the command line while in the main classifier directory:
 
-java -jar stanford-classifier.jar -prop examples/cheese2007.prop
+java -cp "*:." edu.stanford.nlp.classify.ColumnDataClassifier -prop examples/cheese2007.prop
 
 This will classify the included test data, cheeseDisease.test, based on the probability that each example is a cheese or a disease, as calculated by a linear classifier trained on cheeseDisease.train.  
 
@@ -76,6 +76,8 @@ LICENSE
 CHANGES
 -------------------------
 
+2015-12-09    3.6.0     Update for compatibility 
+
 2015-04-20    3.5.2     Update for compatibility 
 
 2015-01-29    3.5.1     New input/output options, support for GloVe 

doc/classify/README.txt

@@ -0,0 +1,6 @@
+Manifest-Version: 1.0
+Implementation-Version: 3.7.0
+Built-Date: 2016-04-27
+Created-By: Stanford JavaNLP
+Main-class: edu.stanford.nlp.pipeline.StanfordCoreNLP
+

doc/corenlp/META-INF/MANIFEST.MF

@@ -42,8 +42,11 @@ LICENSE
 CHANGES
 ---------------------------------
 
+2015-12-09    3.6.0     Improved coreference, OpenIE integration, 
+                        Stanford CoreNLP server 
+
 2015-04-20    3.5.2     Switch to Universal dependencies, add Chinese 
-                        coreference systemCore NLP 
+                        coreference system to CoreNLP 
 
 2015-01-29    3.5.1     NER, dependency parser, SPIED improvements; 
                         general bugfixes 

doc/corenlp/README.txt

@@ -18,5 +18,5 @@ else
   scriptdir=$(dirname "$scriptpath")
 fi
 
-echo java -mx3g -cp \"$scriptdir/*\" edu.stanford.nlp.pipeline.StanfordCoreNLP $*
-java -mx3g -cp "$scriptdir/*" edu.stanford.nlp.pipeline.StanfordCoreNLP $*
+echo java -mx5g -cp \"$scriptdir/*\" edu.stanford.nlp.pipeline.StanfordCoreNLP $*
+java -mx5g -cp "$scriptdir/*" edu.stanford.nlp.pipeline.StanfordCoreNLP $*

doc/corenlp/corenlp.sh

@@ -2,7 +2,7 @@
   <modelVersion>4.0.0</modelVersion>
   <groupId>edu.stanford.nlp</groupId>
   <artifactId>stanford-corenlp</artifactId>
-  <version>3.5.2</version>
+  <version>3.6.0</version>
   <packaging>jar</packaging>
   <name>Stanford CoreNLP</name>
   <description>Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.</description>
@@ -14,8 +14,8 @@
     </license>
   </licenses>
   <scm>
-    <url>http://nlp.stanford.edu/software/stanford-corenlp-2015-04-21.zip</url>
-    <connection>http://nlp.stanford.edu/software/stanford-corenlp-2015-04-21.zip</connection>
+    <url>http://nlp.stanford.edu/software/stanford-corenlp-2015-12-06.zip</url>
+    <connection>http://nlp.stanford.edu/software/stanford-corenlp-2015-12-06.zip</connection>
   </scm>
   <developers>
     <developer>
@@ -24,9 +24,9 @@
       <email>[email protected]</email>
     </developer>
     <developer>
-      <id>john.bauer</id>
-      <name>John Bauer</name>
-      <email>[email protected]</email>
+      <id>jason.bolton</id>
+      <name>Jason Bolton</name>
+      <email>[email protected]</email>
     </developer>
   </developers>
   <properties>
@@ -65,6 +65,11 @@
       <artifactId>slf4j-api</artifactId>
       <version>1.7.12</version>
     </dependency>
+    <dependency>
+      <groupId>com.google.protobuf</groupId>
+      <artifactId>protobuf-java</artifactId>
+      <version>2.6.1</version>
+    </dependency>
   </dependencies>
   <build>
     <sourceDirectory>src</sourceDirectory>
@@ -83,7 +88,7 @@
             <configuration>
               <artifacts>
                 <artifact>
-                  <file>${project.basedir}/stanford-corenlp-3.5.2-models.jar</file>
+                  <file>${project.basedir}/stanford-corenlp-3.6.0-models.jar</file>
                   <type>jar</type>
                   <classifier>models</classifier>
                 </artifact>

doc/corenlp/pom-full.xml

@@ -2,7 +2,7 @@
   <modelVersion>4.0.0</modelVersion>
   <groupId>edu.stanford.nlp</groupId>
   <artifactId>stanford-corenlp</artifactId>
-  <version>3.3.0</version>
+  <version>3.6.0</version>
   <packaging>jar</packaging>
   <name>Stanford CoreNLP</name>
   <description>Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.</description>
@@ -14,8 +14,8 @@
     </license>
   </licenses>
   <scm>
-    <url>http://nlp.stanford.edu/software/stanford-corenlp-2013-11-12.zip</url>
-    <connection>http://nlp.stanford.edu/software/stanford-corenlp-2013-11-12.zip</connection>
+    <url>http://nlp.stanford.edu/software/stanford-corenlp-2015-12-06.zip</url>
+    <connection>http://nlp.stanford.edu/software/stanford-corenlp-2015-12-06.zip</connection>
   </scm>
   <developers>
     <developer>
@@ -24,9 +24,9 @@
       <email>[email protected]</email>
     </developer>
     <developer>
-      <id>john.bauer</id>
-      <name>John Bauer</name>
-      <email>[email protected]</email>
+      <id>jason.bolton</id>
+      <name>Jason Bolton</name>
+      <email>[email protected]</email>
     </developer>
   </developers>
   <properties>

doc/corenlp/pom-light.xml

@@ -1,4 +1,4 @@
-Stanford Lexicalized Parser v3.5.2 - 2015-04-20
+Stanford Lexicalized Parser v3.6.0 - 2015-12-09
 -----------------------------------------------
 
 Copyright (c) 2002-2015 The Board of Trustees of The Leland Stanford Junior
@@ -224,6 +224,8 @@ LICENSE
 CHANGES
 ---------------------------------
 
+2015-12-09    3.6.0     Updated for compatibility 
+
 2015-04-20    3.5.2     Switch to universal dependencies 
 
 2015-01-29    3.5.1     Dependency parser improvements; general 

doc/lexparser/README.txt

@@ -2,7 +2,7 @@
   <modelVersion>4.0.0</modelVersion>
   <groupId>edu.stanford.nlp</groupId>
   <artifactId>stanford-parser</artifactId>
-  <version>3.5.2</version>
+  <version>3.6.0</version>
   <packaging>jar</packaging>
   <name>Stanford Parser</name>
   <description>Stanford Parser processes raw text in English, Chinese, German, Arabic, and French, and extracts constituency parse trees.</description>
@@ -14,8 +14,8 @@
     </license>
   </licenses>
   <scm>
-    <url>http://nlp.stanford.edu/software/stanford-parser-2015-04-20.zip</url>
-    <connection>http://nlp.stanford.edu/software/stanford-parser-2015-04-20.zip</connection>
+    <url>http://nlp.stanford.edu/software/stanford-parser-2015-12-08.zip</url>
+    <connection>http://nlp.stanford.edu/software/stanford-parser-2015-12-08.zip</connection>
   </scm>
   <developers>
     <developer>
@@ -24,9 +24,9 @@
       <email>[email protected]</email>
     </developer>
     <developer>
-      <id>john.bauer</id>
-      <name>John Bauer</name>
-      <email>[email protected]</email>
+      <id>jason.bolton</id>
+      <name>Jason Bolton</name>
+      <email>[email protected]</email>
     </developer>
     <developer>
       <id>spence.green</id>
@@ -45,6 +45,11 @@
       <artifactId>ejml</artifactId>
       <version>0.23</version>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>1.7.12</version>
+    </dependency>
   </dependencies>
   <build>
     <sourceDirectory>src</sourceDirectory>
@@ -63,7 +68,7 @@
             <configuration>
               <artifacts>
                 <artifact>
-                  <file>${project.basedir}/stanford-parser-3.5.2-models.jar</file>
+                  <file>${project.basedir}/stanford-parser-3.6.0-models.jar</file>
                   <type>jar</type>
                   <classifier>models</classifier>
                 </artifact>