swem 0.1.2

A portable document embedding using SWEM.

SWEM

Implementation of SWEM(Simple Word-Embedding-based Models)
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (ACL 2018)

Installation

pip install swem

Example

Examples are available in examples directory.

• simple_embedding_en.py
• simple_embedding_ja.py

Japanese

import swem

from gensim.models import KeyedVectors

if __name__ == '__main__':
    model = KeyedVectors.load('wiki_mecab-ipadic-neologd.kv')
    swem_embed = swem.SWEM(model)

    doc = 'すもももももももものうち'
    embed = swem_embed.infer_vector(doc, method='max')
    print(embed.shape)

Results

(200,)

English

import swem

from gensim.models import KeyedVectors

if __name__ == '__main__':
    model = KeyedVectors.load('wiki_mecab-ipadic-neologd.kv')
    swem_embed = swem.SWEM(model, lang='en')

    doc = 'This is an implementation of SWEM.'
    embed = swem_embed.infer_vector(doc, method='max')
    print(embed.shape)

Results

(200,)