Infinity Future infinityfuture
infinityfuture
/ fasttext_gensim.py
Created
February 6, 2019 14:50
Using Gensim train FastText Chinese Char vector
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pickle | |
| from gensim.models.fasttext import FastText | |
| # [ ['你', '好', '吗'] ] | |
| sentences = pickle.load(open('./x.pkl', 'rb')) | |
| model = FastText(size=64, window=10, min_count=1) | |
| model.build_vocab(sentences=sentences) | |
| model.train(sentences=sentences, total_examples=len(sentences), epochs=10) | |
| model.wv.save_word2vec_format('./fasttext64.txt') |
infinityfuture
/ textrank_summarization_word2vec.py
Created
October 4, 2018 08:11
Use TextRank algorithm to generate summary, using word2vec as sentence similarity
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Reference: | |
| http://www.hankcs.com/nlp/textrank-algorithm-to-extract-the-keywords-java-implementation.html | |
| http://www.hankcs.com/nlp/textrank-algorithm-java-implementation-of-automatic-abstract.html | |
| Chinese Embedding From | |
| https://github.com/Embedding/Chinese-Word-Vectors |
infinityfuture
/ textrank_keywords_word2vec.py
Created
October 4, 2018 08:08
TextRank extract keywords using word2vec as similarity
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Reference: | |
| http://www.hankcs.com/nlp/textrank-algorithm-to-extract-the-keywords-java-implementation.html | |
| http://www.hankcs.com/nlp/textrank-algorithm-java-implementation-of-automatic-abstract.html | |
| Chinese Embedding From | |
| https://github.com/Embedding/Chinese-Word-Vectors |
infinityfuture
/ textrank_summarization.py
Last active
October 4, 2018 08:11
Use TextRank algorithm to generate summary
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Reference: | |
| http://www.hankcs.com/nlp/textrank-algorithm-to-extract-the-keywords-java-implementation.html | |
| http://www.hankcs.com/nlp/textrank-algorithm-java-implementation-of-automatic-abstract.html | |
| """ | |
| from gensim.summarization.bm25 import get_bm25_weights | |
| import numpy as np | |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Reference: | |
| http://www.hankcs.com/nlp/textrank-algorithm-to-extract-the-keywords-java-implementation.html | |
| http://www.hankcs.com/nlp/textrank-algorithm-java-implementation-of-automatic-abstract.html | |
| """ | |
| import numpy as np |
infinityfuture
/ pytorch_global_max_pooling.py
Last active
October 3, 2018 16:47
Pytorch Global Max Pooling
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def global_max_pooling(tensor, dim, topk): | |
| """Global max pooling""" | |
| ret, _ = torch.topk(tensor, topk, dim) | |
| return ret |