gensim   259

« earlier    

bollu/bollu.github.io: everything you know about word2vec is wrong
"[...] this is probably the last time I take a machine learning paper's explanation of the algorithm seriously again --- from next time, I read the source first."
word2vec  sci-pub  gensim  source-first  nlp 
8 days ago by chl
R and Python text analysis packages performance comparison
The performance gain of quanteda’s new architecture became apparent in the head-to-head comparison with gensim. Quanteda’s execution time is around 50% shorter, and peak memory consumption is 40% smaller than gensim.
text_mining  R  Python  quanteda  gensim 
9 weeks ago by mjaniec

« earlier    

related tags

ai  analysis  artificialintelligence  asyncio  aws  blog  blogs  bottle  by:radim-řehůřek  classification  clustering  corpus  data  dataanalysis  datamining  datascience  deep-learning  deeplearning  demo  dl  doc2dev  doc2vec  docker  document  documentation  download  ec2  embedding  embeddings  examples  fasttext  gensimlibrary  glove  infovis  intel  interview  ipynbs  journalism  keras  konlpy  lambda  language  languageanalysis  latentdirichletallocation  lda  learning  legal  lib  library  linguistic  load  lsi  lstm  machine  machinelearning  memory  microbit  ml  model  modeling  mt  naturallanguageprocessing  neuralnets  neuralnetwork  news  nlp  nlproc  nltk  opensource  pandas  podcast  pydataldn  pyparis  python  quanteda  r  reuters  sci-pub  script  semantics  service  similarity  sklearn  source-first  spacy  stackexchange  stackoverflow  statistics  supremcourt  tensorboard  tensorflow  text-analysis  text  text_mining  tfidf  tips  topic-modeling  topic-models  topic  topicmodel  topicmodelling  topicmodels  topics  translation-matrix  tricks  tutorial  tutorials  vocabulary  vsm  wikipedia  with:tomáš-mikolov  wmd  word  word2vec  word_embedding  word_mover_distance  wordembedding  トピック分析  구문분석 

Copy this bookmark:



description:


tags: