airalcorn2/Deep-Semantic-Similarity-Model

Stars
519
Rank 85,261 (Top 2 %)
Language
Python
License
MIT License
Created over 8 years ago
Updated over 7 years ago

airalcorn2/Deep-Semantic-Similarity-Model

airalcorn2

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here: http://research.microsoft.com/pubs/226585/cikm2014_cdssm_final.pdf.

Deep Semantic Similarity Model

My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here. As search data sets are generally proprietary, you will have to provide your own data to use with the code.

Additional References

http://research.microsoft.com/pubs/238873/wsdm2015.v3.pdf - slides giving a high level overview of the DSSM and how it can be used for information retrieval.
http://research.microsoft.com/en-us/projects/dssm/ - Microsoft Research's summary of the DSSM (includes many more references).

Michael-s-Data-Science-Curriculum

This is the companion curriculum to my guide to becoming a data scientist.

RankNet

My (slightly modified) Keras implementation of RankNet and PyTorch implementation of LambdaRank.

pytorch-nerf

Minimal PyTorch implementations of NeRF and pixelNeRF.

Recurrent-Convolutional-Neural-Network-Text-Classifier

My (slightly modified) Keras implementation of the Recurrent Convolutional Neural Network (RCNN) described here: http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9745.

Solr-LTR

From Zero to Learning to Rank in Apache Solr

batter-pitcher-2vec

A model for learning distributed representations of MLB players.

Jupyter Notebook

strike-with-a-pose

A simple GUI tool for generating adversarial poses of objects.

baller2vec

A multi-entity Transformer for multi-agent spatiotemporal modeling.

Michael-s-Guide-to-Becoming-a-Data-Scientist

I was once asked about transitioning to a career in data science by three different UChicago grad students over a short period of time, so I decided to put together this outline in case anyone else was curious.

baller2vecplusplus

A look-ahead multi-entity Transformer for modeling coordinated agents.

pytorch-geodesic-loss

A PyTorch criterion for computing the distance between rotation matrices.

Color-Names

An improved version of the color name model described here: http://lewisandquark.tumblr.com/post/160776374467/new-paint-colors-invented-by-neural-network.

vqvae-pytorch

A minimal PyTorch implementation of the VQ-VAE model described in "Neural Discrete Representation Learning".

LMIR

Pure Python implementations of the language models for information retrieval surveyed here: https://dl.acm.org/doi/10.1145/383952.384019.

Football-o-Genetics

An application for "evolving" near-optimal offensive play calling strategies.

paved2paradise

Cost-effective and scalable LiDAR simulation by factoring the real world.

deformer

An order-agnostic distribution estimating Transformer.

shallow-deep-learning

The code and slides for my "A Shallow Introduction to Deep Learning" workshop.

pytorch-ipdf

Minimal PyTorch implementation of implicit-PDF.

Hangouts-NLP

A program that performs a number of different natural language processing analyses on Google Hangouts instant messaging data.

Sequences-With-Sentences

A convolutional recurrent neural network that can handle data sequences containing a mixture of fixed size and variable size (e.g., text) inputs at each time step.

ScatterPlot3D

An application for visualizing and exploring three-dimensional scatter plot data.

boformer

pytorch-volume-rotator

Applies explicit 3D transformations to feature volumes in PyTorch.

aquamam

An autoregressive, quaternion manifold model for rapidly estimating complex SO(3) distributions.

parking-lot-pointnetplusplus

Train a PointNet++ bounding box regression model on parking lot samples obtained by following the Paved2Paradise protocol.