A Java implementation of doc2vec in ICML'14
Clone or download
Latest commit f8e316e Jul 23, 2015
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.settings first commit Jul 12, 2015
bin first commit Jul 12, 2015
file first commit Jul 12, 2015
lib first commit Jul 12, 2015
model Add model Jul 12, 2015
src Update LearnDocVec.java Jul 23, 2015
.classpath first commit Jul 12, 2015
.project first commit Jul 12, 2015
README.md Better Strucutre in README.md Jul 12, 2015

README.md

doc2vec_java

A Java implementation of doc2vec in ICML'14 based on https://github.com/NLPchina/Word2VEC_java

demo

src/test/Doc2VecTest.java

Require

Java 7 or above, I use Java 8 in this project. The input file should be in the form of file/amazon_docs.txt. One document per line.

Reference

  1. Le, Quoc V., and Tomas Mikolov. "Distributed representations of sentences and documents." ICML (2014).
  2. Mikolov, Tomas, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. "Distributed representations of words and phrases and their compositionality." In Advances in neural information processing systems, pp. 3111-3119. 2013.