1

### jwieting/iclr2016: Python code for training all models in the ICLR paper, "Towards Universal Paraphrastic Sentence Embeddings - John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu". These models achieve strong performance on semantic similarity tasks

[2 commits @ 84 days - 72 days ago] (github.com)
1

### jayhack/LSTMVRAE: Variational Recurrent Auto-Encoder using LSTM encoder/decoder networks

[2 commits @ 2 hours - 2 hours ago] (github.com)
1

### gregversteeg/discrete_sieve: The information sieve for discrete variables. Build maximally informative representations in an incremental way. Apply to independent component analysis, lossy and lossless compression, and predicting missing values in data.

[7 commits @ 11 months - 15 days ago] (github.com)See also:

Papers:
Discovering Structure in High-Dimensional Data Through Correlation Explanation - Greg Ver Steeg, Aram Galstyan
(arxiv.org)
0 Comments

Papers:
Maximally Informative Hierarchical Representations of High-Dimensional Data - Greg Ver Steeg, Aram Galstyan
(arxiv.org)
0 Comments

1

### jwieting/paragram-word: Python code for training Paragram word embeddings. These achieve human-level performance on some word similiarty tasks including SimLex-999.This code was used to obtain results in the appendix of our 2015 TACL paper "From Paraphrase

[2 commits @ 94 days - 87 days ago] (github.com)
1