├── .classpath
├── .gitignore
├── .project
├── .settings
    ├── org.eclipse.core.resources.prefs
    ├── org.eclipse.jdt.core.prefs
    └── org.eclipse.m2e.core.prefs
├── README.md
├── pom.xml
└── src
    ├── main
        └── java
        │   └── drew
        │       └── corenlp
        │           ├── SimpleExample.java
        │           └── TruecaseExample.java
    └── test
        └── resources
            └── sample-content.txt


/.classpath:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <classpath>
 3 | 	<classpathentry kind="src" output="target/classes" path="src/main/java">
 4 | 		<attributes>
 5 | 			<attribute name="optional" value="true"/>
 6 | 			<attribute name="maven.pomderived" value="true"/>
 7 | 		</attributes>
 8 | 	</classpathentry>
 9 | 	<classpathentry excluding="**" kind="src" output="target/classes" path="src/main/resources">
10 | 		<attributes>
11 | 			<attribute name="maven.pomderived" value="true"/>
12 | 		</attributes>
13 | 	</classpathentry>
14 | 	<classpathentry kind="src" output="target/test-classes" path="src/test/java">
15 | 		<attributes>
16 | 			<attribute name="optional" value="true"/>
17 | 			<attribute name="maven.pomderived" value="true"/>
18 | 		</attributes>
19 | 	</classpathentry>
20 | 	<classpathentry excluding="**" kind="src" output="target/test-classes" path="src/test/resources">
21 | 		<attributes>
22 | 			<attribute name="maven.pomderived" value="true"/>
23 | 		</attributes>
24 | 	</classpathentry>
25 | 	<classpathentry kind="con" path="org.eclipse.m2e.MAVEN2_CLASSPATH_CONTAINER">
26 | 		<attributes>
27 | 			<attribute name="maven.pomderived" value="true"/>
28 | 		</attributes>
29 | 	</classpathentry>
30 | 	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.6">
31 | 		<attributes>
32 | 			<attribute name="maven.pomderived" value="true"/>
33 | 		</attributes>
34 | 	</classpathentry>
35 | 	<classpathentry kind="output" path="target/classes"/>
36 | </classpath>
37 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | target
2 | .idea
3 | *.iml
4 | 


--------------------------------------------------------------------------------
/.project:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <projectDescription>
 3 | 	<name>corenlp-example</name>
 4 | 	<comment></comment>
 5 | 	<projects>
 6 | 	</projects>
 7 | 	<buildSpec>
 8 | 		<buildCommand>
 9 | 			<name>org.eclipse.jdt.core.javabuilder</name>
10 | 			<arguments>
11 | 			</arguments>
12 | 		</buildCommand>
13 | 		<buildCommand>
14 | 			<name>org.eclipse.m2e.core.maven2Builder</name>
15 | 			<arguments>
16 | 			</arguments>
17 | 		</buildCommand>
18 | 	</buildSpec>
19 | 	<natures>
20 | 		<nature>org.eclipse.jdt.core.javanature</nature>
21 | 		<nature>org.eclipse.m2e.core.maven2Nature</nature>
22 | 	</natures>
23 | </projectDescription>
24 | 


--------------------------------------------------------------------------------
/.settings/org.eclipse.core.resources.prefs:
--------------------------------------------------------------------------------
1 | eclipse.preferences.version=1
2 | encoding//src/main/java=UTF-8
3 | encoding//src/main/resources=UTF-8
4 | encoding//src/test/java=UTF-8
5 | encoding//src/test/resources=UTF-8
6 | encoding/<project>=UTF-8
7 | 


--------------------------------------------------------------------------------
/.settings/org.eclipse.jdt.core.prefs:
--------------------------------------------------------------------------------
1 | eclipse.preferences.version=1
2 | org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.6
3 | org.eclipse.jdt.core.compiler.compliance=1.6
4 | org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning
5 | org.eclipse.jdt.core.compiler.source=1.6
6 | 


--------------------------------------------------------------------------------
/.settings/org.eclipse.m2e.core.prefs:
--------------------------------------------------------------------------------
1 | activeProfiles=
2 | eclipse.preferences.version=1
3 | resolveWorkspaceProjects=true
4 | version=1
5 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | corenlp-examples
2 | ================
3 | 
4 | Stanford Core NLP API usage examples
5 | 


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
 1 | <project xmlns="http://maven.apache.org/POM/4.0.0" 
 2 |   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 3 |   xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 4 | 
 5 |   <modelVersion>4.0.0</modelVersion>
 6 |   <groupId>drew</groupId>
 7 |   <artifactId>corenlp-example</artifactId>
 8 |   <version>1</version>
 9 |   <name>Simple Stanford CoreNLP/Parser examples</name>
10 |   <description>Examples of Stanford Core NLP and Stanford Parser API usage </description>
11 | 
12 |   <properties>
13 |     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
14 |   </properties>
15 | 
16 |   <build>
17 |     <plugins>
18 |       <plugin>
19 |         <groupId>org.apache.maven.plugins</groupId>
20 |         <artifactId>maven-compiler-plugin</artifactId>
21 |         <configuration>
22 |           <source>1.6</source>
23 |           <target>1.6</target>
24 |         </configuration>
25 |         <version>3.0</version>
26 |       </plugin>
27 |     </plugins>
28 |   </build>
29 |   <dependencies>
30 |     <dependency>
31 |       <groupId>edu.stanford.nlp</groupId>
32 |       <artifactId>stanford-corenlp</artifactId>
33 |       <version>4.4.0</version>
34 |     </dependency>
35 |     <dependency>
36 |       <groupId>edu.stanford.nlp</groupId>
37 |       <artifactId>stanford-corenlp</artifactId>
38 |       <version>4.4.0</version>
39 |       <classifier>models</classifier>
40 |     </dependency>
41 |     <dependency>
42 |       <groupId>edu.stanford.nlp</groupId>
43 |       <artifactId>stanford-parser</artifactId>
44 |       <version>3.9.2</version>
45 |     </dependency>
46 |     <dependency>
47 |       <groupId>com.google.guava</groupId>
48 |       <artifactId>guava</artifactId>
49 |       <version>31.0.1-jre</version>
50 |     </dependency>
51 |     <dependency>
52 |       <groupId>org.slf4j</groupId>
53 |       <artifactId>slf4j-simple</artifactId>
54 |       <version>1.7.12</version>
55 |       <scope>runtime</scope>
56 |       <optional>true</optional>
57 |     </dependency>
58 |   </dependencies>
59 | </project>
60 | 


--------------------------------------------------------------------------------
/src/main/java/drew/corenlp/SimpleExample.java:
--------------------------------------------------------------------------------
 1 | package drew.corenlp;
 2 | 
 3 | import java.io.File;
 4 | import java.io.IOException;
 5 | import java.nio.charset.Charset;
 6 | import java.util.List;
 7 | import java.util.Map;
 8 | import java.util.Properties;
 9 | 
10 | import com.google.common.io.Files;
11 | 
12 | import edu.stanford.nlp.dcoref.CorefChain;
13 | import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
14 | import edu.stanford.nlp.ling.CoreAnnotations.NamedEntityTagAnnotation;
15 | import edu.stanford.nlp.ling.CoreAnnotations.PartOfSpeechAnnotation;
16 | import edu.stanford.nlp.ling.CoreAnnotations.SentencesAnnotation;
17 | import edu.stanford.nlp.ling.CoreAnnotations.TextAnnotation;
18 | import edu.stanford.nlp.ling.CoreAnnotations.TokensAnnotation;
19 | import edu.stanford.nlp.ling.CoreLabel;
20 | import edu.stanford.nlp.pipeline.Annotation;
21 | import edu.stanford.nlp.pipeline.StanfordCoreNLP;
22 | import edu.stanford.nlp.semgraph.SemanticGraph;
23 | import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
24 | import edu.stanford.nlp.trees.Tree;
25 | import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
26 | import edu.stanford.nlp.util.CoreMap;
27 | 
28 | /** A simple corenlp example ripped directly from the Stanford CoreNLP website using text from wikinews. */
29 | public class SimpleExample {
30 | 
31 |   public static void main(String[] args) throws IOException {
32 |     // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution 
33 |     Properties props = new Properties();
34 |     props.put("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref");
35 |     StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
36 |     
37 |     // read some text from the file..
38 |     File inputFile = new File("src/test/resources/sample-content.txt");
39 |     String text = Files.asCharSource(inputFile, Charset.forName("UTF-8")).read();
40 | 
41 |     // create an empty Annotation just with the given text
42 |     Annotation document = new Annotation(text);
43 | 
44 |     // run all Annotators on this text
45 |     pipeline.annotate(document);
46 | 
47 |     // these are all the sentences in this document
48 |     // a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
49 |     List<CoreMap> sentences = document.get(SentencesAnnotation.class);
50 | 
51 |     for(CoreMap sentence: sentences) {
52 |       // traversing the words in the current sentence
53 |       // a CoreLabel is a CoreMap with additional token-specific methods
54 |       for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
55 |         // this is the text of the token
56 |         String word = token.get(TextAnnotation.class);
57 |         // this is the POS tag of the token
58 |         String pos = token.get(PartOfSpeechAnnotation.class);
59 |         // this is the NER label of the token
60 |         String ne = token.get(NamedEntityTagAnnotation.class);
61 |         
62 |         System.out.println("word: " + word + " pos: " + pos + " ne:" + ne);
63 |       }
64 | 
65 |       // this is the parse tree of the current sentence
66 |       Tree tree = sentence.get(TreeAnnotation.class);
67 |       System.out.println("parse tree:\n" + tree);
68 | 
69 |       // this is the Stanford dependency graph of the current sentence
70 |       SemanticGraph dependencies = sentence.get(CollapsedCCProcessedDependenciesAnnotation.class);
71 |       System.out.println("dependency graph:\n" + dependencies);
72 |     }
73 | 
74 |     // This is the coreference link graph
75 |     // Each chain stores a set of mentions that link to each other,
76 |     // along with a method for getting the most representative mention
77 |     // Both sentence and token offsets start at 1!
78 |     Map<Integer, CorefChain> graph = 
79 |         document.get(CorefChainAnnotation.class);
80 |     
81 |   }
82 | 
83 | }
84 | 


--------------------------------------------------------------------------------
/src/main/java/drew/corenlp/TruecaseExample.java:
--------------------------------------------------------------------------------
  1 | package drew.corenlp;
  2 | 
  3 | import com.google.common.io.Files;
  4 | import edu.stanford.nlp.dcoref.CorefChain;
  5 | import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
  6 | import edu.stanford.nlp.ling.CoreAnnotations.*;
  7 | import edu.stanford.nlp.ling.CoreLabel;
  8 | import edu.stanford.nlp.pipeline.Annotation;
  9 | import edu.stanford.nlp.pipeline.StanfordCoreNLP;
 10 | import edu.stanford.nlp.semgraph.SemanticGraph;
 11 | import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
 12 | import edu.stanford.nlp.trees.Tree;
 13 | import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
 14 | import edu.stanford.nlp.util.CoreMap;
 15 | 
 16 | import java.io.File;
 17 | import java.io.IOException;
 18 | import java.nio.charset.Charset;
 19 | import java.util.ArrayList;
 20 | import java.util.List;
 21 | import java.util.Map;
 22 | import java.util.Properties;
 23 | 
 24 | /** A simple corenlp example ripped directly from the Stanford CoreNLP website using text from wikinews. */
 25 | public class TruecaseExample {
 26 | 
 27 |   public static void main(String[] args) throws IOException {
 28 |     // creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution 
 29 |     Properties props = new Properties();
 30 |     props.put("annotators", "tokenize, ssplit, pos, lemma, truecase");
 31 |     StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
 32 | 
 33 |     // read some text from the file..
 34 |     File inputFile = new File("src/test/resources/sample-content.txt");
 35 |     String input = Files.toString(inputFile, Charset.forName("UTF-8"));
 36 |     String lcInput = input.toLowerCase(); // downcase everything.
 37 | 
 38 |     // create an empty Annotation with just the downcased text.
 39 |     Annotation document = new Annotation(lcInput);
 40 | 
 41 |     // run all Annotators on this text
 42 |     pipeline.annotate(document);
 43 | 
 44 |     // these are all the sentences in this document
 45 |     // a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
 46 |     List<CoreMap> sentences = document.get(SentencesAnnotation.class);
 47 | 
 48 |     // capture the true cased tokens for evaluation.
 49 |     List<String> tcTokens = new ArrayList<String>();
 50 | 
 51 |     System.out.println("------ begin truecase output -----");
 52 |     for (CoreMap sentence : sentences) {
 53 |       // traversing the words in the current sentence
 54 |       // a CoreLabel is a CoreMap with additional token-specific methods
 55 |       for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
 56 |         // this is the text of the token
 57 |         String text = token.get(TextAnnotation.class);
 58 |         String trueCase = token.get(TrueCaseAnnotation.class);
 59 |         String trueCaseText = token.get(TrueCaseTextAnnotation.class);
 60 |         System.out.printf("input:%s state:%s output:%s\n", text, trueCase, trueCaseText);
 61 |         tcTokens.add(trueCaseText);
 62 |       }
 63 |     }
 64 |     System.out.println("------ end truecase otuput -----");
 65 | 
 66 | 
 67 |     // create an empty Annotation with just the standard text.
 68 |     document = new Annotation(input);
 69 | 
 70 |     // run all Annotators on this text
 71 |     pipeline.annotate(document);
 72 |     sentences = document.get(SentencesAnnotation.class);
 73 | 
 74 |     // capture the standard tokens for evaluation - note this assumes that
 75 |     // the pipeline won't generate additional tokens for the same input.
 76 |     List<String> stdTokens = new ArrayList<String>();
 77 | 
 78 |     for (CoreMap sentence : sentences) {
 79 |       // traversing the words in the current sentence
 80 |       // a CoreLabel is a CoreMap with additional token-specific methods
 81 |       for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
 82 |         // this is the text of the token
 83 |         String word = token.get(TextAnnotation.class);
 84 |         stdTokens.add(word);
 85 |       }
 86 |     }
 87 | 
 88 |     // compare the output of the tc and the original to see how well we've done
 89 |     int match = 0;
 90 |     int sz = tcTokens.size();
 91 | 
 92 |     System.out.println("------ begin evaluation output -----");
 93 | 
 94 |     for (int i=0; i < sz; i++) {
 95 |       String tcToken = tcTokens.get(i);
 96 |       String stdToken = stdTokens.get(i);
 97 |       if (tcToken.equals(stdToken)) {
 98 |         match++;
 99 |       }
100 |       else {
101 |         System.out.printf("Truecase mismatch: input:'%s' output:'%s' @ %d\n", stdToken, tcToken, i);
102 |       }
103 |     }
104 | 
105 |     float errorRate = ((float) sz - match) / sz;
106 |     System.out.println("Error Rate: " + errorRate);
107 | 
108 |     System.out.println("------ end evaluation output -----");
109 |   }
110 | }
111 | 


--------------------------------------------------------------------------------
/src/test/resources/sample-content.txt:
--------------------------------------------------------------------------------
 1 | Last night, Adly Mansour, the interim leader of Egypt, announced plans to 
 2 | reform Egypt's constitution and hold a new round of parliamentary and 
 3 | presidential elections. The interim president also announced a judicial 
 4 | investigation into yesterday's shooting of at least 51 supporters of deposed 
 5 | president Mohamed Morsi. 
 6 | 
 7 | Mansour plans to form a panel within fifteen days to review and suggest changes
 8 | to the now-suspended constitution. Those amendments would be voted on in a 
 9 | referendum within four months. Parliamentary elections would then be held, 
10 | perhaps in early 2014, followed by presidential elections upon the forming 
11 | of a new parliament.""
12 | 


--------------------------------------------------------------------------------