Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Word2Vec #12

Open
2 of 4 tasks
Bomberus opened this issue Mar 2, 2017 · 3 comments
Open
2 of 4 tasks

Word2Vec #12

Bomberus opened this issue Mar 2, 2017 · 3 comments
Assignees

Comments

@Bomberus
Copy link

Bomberus commented Mar 2, 2017

  • Kapitel in Arbeit
  • Motivation
  • Hintergrund
  • Client für Python Programm
@Bomberus Bomberus closed this as completed Mar 2, 2017
@Bomberus Bomberus reopened this Mar 2, 2017
@Bomberus Bomberus self-assigned this Mar 2, 2017
@ScientiaEtVeritas ScientiaEtVeritas self-assigned this Mar 2, 2017
@ScientiaEtVeritas
Copy link
Contributor

Paragraph Vectors scheinen ein guter Weg zu sein:
https://cs.stanford.edu/~quocle/paragraph_vector.pdf
http://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf
Vector Averging wird auch erwähnt, also auch mal ausprobieren.

@Bomberus
Copy link
Author

Bomberus commented Mar 4, 2017

Clientprogramm nutzt Sockets um mit Server zu kommunizieren und Client + Server belegen ~ 5.1 GB RAM. Die Daten können im folgenden Schema aufgrufen werden:

from word2vec import Word2Vec

word2vec = Word2Vec()

word2vec.connect()

print(word2vec.similar_by_word(word="la"))

word2vec.close()

Werde am Sonntag Projekt in Github pushen und auf den Server aufspielen.

@Bomberus
Copy link
Author

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants