vhoulbreque / fasttext-tuning

Related projects ⓘ

Alternatives and complementary repositories for fasttext-tuning

• ArdalanM / gensim2tensorboard
  Train word embeddings with Gensim and vizualize them with TensorBoard
  ☆34Updated 5 years ago
• cedricdeboom / RepresentationLearning
  Code base for representation learning of very short texts, such as tweets. By Cedric De Boom, IBCN, Ghent University, Belgium.
  ☆37Updated 8 years ago
• AlanAnsell / PolyLM
  ☆15Updated 3 years ago
• mheilman / tan-clustering
  Hierarchical word clustering, following "Brown clustering" (Brown et al., 1992)
  ☆69Updated 9 years ago
• BramVanroy / spacy-extreme
  An example of how to use spaCy for extremely large files without running into memory issues
  ☆36Updated 2 years ago
• nickdavidhaynes / spacy-cld
  Language detection extension for spaCy 2.0+
  ☆111Updated 5 years ago
• laugustyniak / textlytics
  Text processing library for sentiment analysis and related tasks
  ☆27Updated 6 years ago
• thomsonreuters / attr2vec
  TensorFlow implementation of an arbitrary order Factorization Machine
  ☆19Updated 6 years ago
• opener-project / VU-sentiment-lexicon
  Python library providing sentiment lexicons.
  ☆26Updated 7 years ago
• yuhsinliu1993 / VDCNN
  Using keras to implement VDCNN model
  ☆22Updated 7 years ago
• Noahs-ARK / idea_relations
  A framework to identify relations between ideas in temporal text corpora.
  ☆29Updated 6 years ago
• orenmel / word2parvec
  A toolkit for generating paraphrase vector representations for words in context
  ☆24Updated 9 years ago
• gamebusterz / French-Sentiment-Analysis-Dataset
  A collection of over 1.5 Million tweets data translated to French, with their sentiment.
  ☆35Updated 7 years ago
• BoPengGit / LDA-Doc2Vec-example-with-PCA-LDAvis-visualization
  ☆37Updated 8 years ago
• jhlau / twitter-deepgeo
  Tensorflow code to train and predict geolocation of tweets; network also produces compact representation of tweets for hashing purposes
  ☆16Updated 6 months ago
• chop-dbhi / twitter-adr-blstm
  A model for finding mentions of adverse drug reactions in Twitter posts
  ☆33Updated 6 years ago
• beefoo / text-analysis
  ☆40Updated 9 years ago
• composes-toolkit / dissect
  ☆54Updated 9 years ago
• jaredks / tweetokenize
  Tokenization and pre-processing for Twitter data used to train classifiers.
  ☆71Updated 8 years ago
• cmry / omesa
  Experiment, Storage and Visualization Framework for Machine Learning research.
  ☆31Updated 3 years ago
• ltgoslo / simple_elmo_training
  Minimal code to train ELMo models in recent versions of TensorFlow
  ☆14Updated last year
• olafmaas / hackdelft
  HackDelft
  ☆81Updated 7 years ago
• spinningbytes / deep-mlsa
  Code for WWW 2017 conference paper "Leveraging large amounts of weakly supervised data for multi-language sentiment classification"
  ☆36Updated 5 years ago
• jayantj / gensim
  Topic Modelling for Humans
  ☆40Updated 6 years ago
• short-edition / syntaxnet-wrapper
  Wrapper to use syntaxnet with pre-trained model
  ☆29Updated 6 years ago
• afshinrahimi / activelearning
  Active Learning for text classification using scikit-learn
  ☆23Updated 5 years ago
• marcoguerini / DepecheMood
  High-coverage and high-precision lexica of terms annotated with emotion scores for English and Italian.
  ☆152Updated 3 weeks ago
• benhamner / nips-papers
  ☆29Updated 4 years ago
• sindbach / doc2vec_pymongo
  Machine learning prediction of movies genres using Gensim's Doc2Vec and PyMongo - (Python, MongoDB)
  ☆36Updated last year
• explosion / spacy-benchmarks
  💫 Runtime performance comparison of spaCy against other NLP libraries
  ☆20Updated 2 years ago