https://github.com/chen0040/java-text-embedding
Word embedding in Java
https://github.com/chen0040/java-text-embedding
document-embedding glove glove-embeddings word-embeddings
Last synced: 6 months ago
JSON representation
Word embedding in Java
- Host: GitHub
- URL: https://github.com/chen0040/java-text-embedding
- Owner: chen0040
- License: mit
- Created: 2018-03-05T00:12:07.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2021-03-15T08:25:30.000Z (almost 5 years ago)
- Last Synced: 2023-07-26T21:56:13.759Z (over 2 years ago)
- Topics: document-embedding, glove, glove-embeddings, word-embeddings
- Language: Java
- Size: 55.7 KB
- Stars: 5
- Watchers: 4
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# java-word-embedding
Word embedding in Java
The current project provides GloVe word embedding that developer can directly use within their project.
# Install
Add the following dependency to your POM file:
```xml
com.github.chen0040
java-text-embedding
1.0.1
```
# Usage
The [sample codes](src/main/java/com/github/chen0040/embeddings/GloVeModelDemo.java) below shows how to use
[GloVeModel](src/main/java/com/github/chen0040/embeddings/GloVeModel.java) to create GloVe word embedding of different
dimensions (e.g., 50, 100, 200, 300)
```java
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.github.chen0040.embeddings.GloVeModel;
public class GloVeModelDemo {
private static final Logger logger = LoggerFactory.getLogger(GloVeModelDemo.class);
public static void main(String[] args) {
GloVeModel model = new GloVeModel();
model.load100();
logger.info("word2em size: {}", model.size());
logger.info("word2em dimension for individual word: {}", model.getWordVecDimension());
logger.info("father: {}", model.encodeWord("father"));
logger.info("mother: {}", model.encodeWord("mother"));
logger.info("man: {}", model.encodeWord("man"));
logger.info("woman: {}", model.encodeWord("woman"));
logger.info("boy: {}", model.encodeWord("boy"));
logger.info("girl: {}", model.encodeWord("girl"));
logger.info("distance between boy and girl: {}", model.distance("boy", "girl"));
String doc = "The Zen of Python. Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Flat is better than nested. Sparse is better than dense. Readability counts. Special cases aren't special enough to break the rules.";
logger.info("doc: {}", model.encodeDocument(doc));
}
}
```