piskvorky/gensim

sent2vec in Gensim

Open

#1,376 opened on May 31, 2017

View on GitHub
 (19 comments) (8 reactions) (0 assignees)Python (15,144 stars) (4,349 forks)batch import
difficulty hardhelp wantedwishlist

Description

The EPFL ML group have come up with a sentence embedding technique, sent2vec. The repo with the code can be found here.

It would be interesting to have this feature in Gensim, either with a wrapper or otherwise.

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PythonGensim internalsWord embeddingsNeural networks
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
Investigate the sent2vec paper and the existing C++ implementation. Explore how to integrate it into Gensim's existing word embedding classes (e.g., Word2Vec, Doc2Vec). Look at the issue comments for any suggested approaches or challenges. Consider starting with a wrapper around the original implementation, then aim for a native Python implementation using NumPy for performance.