Crfsuite for Java

Jcrfsuite is a Java interface for crfsuite, a fast implementation of Conditional Random Fields, using SWIG and class injection technique

License

License

Apache License 2.0
BSD License
GroupId

GroupId

com.github.vinhkhuc
ArtifactId

ArtifactId

jcrfsuite
Last Version

Last Version

0.6.1
Release Date

Release Date

Type

Type

jar
Description

Description

Crfsuite for Java
Jcrfsuite is a Java interface for crfsuite, a fast implementation of Conditional Random Fields, using SWIG and class injection technique
Project URL

Project URL

http://maven.apache.org
Source Code Management

Source Code Management

https://github.com/vinhkhuc/jcrfsuite

Download jcrfsuite

How to add to project

<!-- https://jarcasting.com/artifacts/com.github.vinhkhuc/jcrfsuite/ -->
<dependency>
    <groupId>com.github.vinhkhuc</groupId>
    <artifactId>jcrfsuite</artifactId>
    <version>0.6.1</version>
</dependency>
// https://jarcasting.com/artifacts/com.github.vinhkhuc/jcrfsuite/
implementation 'com.github.vinhkhuc:jcrfsuite:0.6.1'
// https://jarcasting.com/artifacts/com.github.vinhkhuc/jcrfsuite/
implementation ("com.github.vinhkhuc:jcrfsuite:0.6.1")
'com.github.vinhkhuc:jcrfsuite:jar:0.6.1'
<dependency org="com.github.vinhkhuc" name="jcrfsuite" rev="0.6.1">
  <artifact name="jcrfsuite" type="jar" />
</dependency>
@Grapes(
@Grab(group='com.github.vinhkhuc', module='jcrfsuite', version='0.6.1')
)
libraryDependencies += "com.github.vinhkhuc" % "jcrfsuite" % "0.6.1"
[com.github.vinhkhuc/jcrfsuite "0.6.1"]

Dependencies

test (2)

Group / Artifact Type Version
junit : junit jar 4.11
org.hamcrest : hamcrest-library jar 1.3

Project Modules

There are no modules declared in this project.

This is a Java interface for crfsuite, a fast implementation of Conditional Random Fields, using SWIG and class injection technique (the same technique used in snappy-java). Jcrfsuite provides API for loading trained model into memory and do sequential tagging in memory. Model training is done via command line interface.

The library is designed for building Java applications for fast text sequential tagging such as Part-Of-Speech (POS) tagging, phrase chunking, Named-Entity Recognition (NER), etc.

Jcrfsuite can be dropped into any Java web applications and run without problem with JVM's class loader.

Maven dependency

<dependency>
  <groupId>com.github.vinhkhuc</groupId>
  <artifactId>jcrfsuite</artifactId>
  <version>0.6.1</version>
</dependency>

Building

git clone https://github.com/vinhkhuc/jcrfsuite
cd jcrfsuite
mvn clean package

How to use

Model training

import com.github.jcrfsuite.CrfTrainer;
...
String trainFile = "data/tweet-pos/train-oct27.txt";
String modelFile = "twitter-pos.model";
CrfTrainer.train(trainFile, modelFile);

Sequential tagging

import com.github.jcrfsuite.CrfTagger;
import com.github.jcrfsuite.util.Pair;
...
String modelFile = "twitter-pos.model";
String testFile = "data/tweet-pos/test-daily547.txt";
CrfTagger crfTagger = new CrfTagger(modelFile);
List<List<Pair<String, Double>>> tagProbLists = crfTagger.tag(testFile);

Example on Twitter Part-Of-Speech tagging

Training

To train a POS model from Twitter POS data, run

java -cp target/jcrfsuite-*.jar com.github.jcrfsuite.example.Train data/tweet-pos/train-oct27.txt twitter-pos.model

Tagging

To test the trained POS model against the test set, run

java -cp target/jcrfsuite-*.jar com.github.jcrfsuite.example.Tag twitter-pos.model data/tweet-pos/test-daily547.txt

The output should be as follows:

Gold	Predict	Probability
........................
N       N       0.99
P       P       1.00
Z       ^       0.59
$       $       0.97
N       N       1.00
P       P       0.98
A       N       0.80
$       $       1.00
N       N       0.99
U       U       1.00

Accuracy = 92.99%

Note that the accuracy might be slightly different than in the above output.

License

Jcrfsuite is released under the Apache License 2.0. The original crfsuite is distributed under the BSD License.

Versions

Version
0.6.1
0.6