Blog Directory
Top level » Software » Natural Language Processing & Information Extraction » Word and document embeddings Facebook's FAST TEXT   FastText   - library for efficient text classification and representation learning. Hierarchical-Neural-Autoencoder   - Implementations of the three models presented in the paper "A Hierarchical Neural Autoencoder for Paragraphs and Documents" by Jiwei Li, Minh-Thang Luong and Dan Jurafsky, ACL 2015 Implementation of a deep recursive net over binary parse trees (code for NIPS2014 paper)  Ozan Irsoy item2vec: Tensorflow implementation   Python implementation of Word Movers Distance (WMD)   SERT   - semantic retrieval toolkit Skip-thought vectors  Ryan Kiros Starspace   - Learning embeddings for classification, retrieval and ranking. TensorFlow implementation of skip-thought model   text2vec  an R package which provides an efficient framework with a concise API for text analysis and natural language processing (NLP). - an R package which provides an efficient framework with a concise API for text analysis and natural language processing (NLP). Tweet2Vec   - Learning tweet embeddings using character-level CNN-LSTM encoder-decoder. Tweet2Vec   - Character-Based Distributed Representations for Social Media. wang2vec  Extension of the original word2vec using different architectures Word Mover's Distance (WMD)  Matthew J Kusner word2vec   - This is an original word2vec on GitHub (maitained by Dav Yaginuma et al) word2vecf   - a modification of Mikolov's word2vec, which, among other things, can learn embeddings for arbitrary contexts.