sent2vec in Gensim · piskvorky/gensim#1376

(19 comments) (8 reactions) (0 assignees)Python (15,144 stars) (4,349 forks)batch import

difficulty hardhelp wantedwishlist

説明

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.

技術スタック: python
領域: machine learning
Issue 種別: feature
難度: 5
推定時間: over 1 week
活動状況: stale
明確さ: mostly clear
前提条件: PythonGensim internalsWord embeddingsNeural networks
初心者向け度: 20
調査方針: 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.