183 Open source projects that are alternatives of or similar to SPINE

Python package to visualize and cluster partial dependence.

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

Clasificador de preguntas escrito en python 3 que fue implementado en el siguiente vídeo: https://youtu.be/qnlW1m6lPoY

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

Concept Bottleneck Models, ICML 2020

Text Similarity Applied to resume, to compare Resumes with Job Descriptions and create a score to rank them. Similar to an ATS.

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)

Sentiment analysis of tweets in Russian using Convolutional Neural Networks (CNN) with Word2Vec embeddings.

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

Context Encoders (ConEc) as a simple but powerful extension of the word2vec model for learning word embeddings

Benchmarks for intrinsic word embeddings evaluation.

Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec from this paper https://arxiv.org/abs/1605.02019

Danish Semantic analysis

SIGIR 2017: Embedding-based query expansion for weighted sequential dependence retrieval model

Code for Supervised Word Mover's Distance (SWMD)

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Global-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.

🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

Code for the paper: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors, ICLR 2019.

official implementation of "Visualization of Convolutional Neural Networks for Monocular Depth Estimation"

[KDD 2020] Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

For calculating global feature importance using Shapley values.

Tools for shrinking fastText models (in gensim format)

[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance

Code for EMNLP 2016 paper: Morphological Priors for Probabilistic Word Embeddings

PyTorch implementation of context2vec from Melamud et al., CoNLL 2016

Arabic Word Embeddings Word2vec

A library for finding knowledge neurons in pretrained transformer models.

Code for "Free-Lunch Saliency via Attention in Atari Agents"

Train Wikidata with word2vec for word embedding tasks

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

Codenames AI using Word Vectors

Contextual LSTM for NLP tasks like word prediction and word embedding creation for Deep Learning

Public release of data and code for materials synthesis generation

A pipeline for training word embeddings using word2vec on wikipedia corpus.

Yelp round-10 review comments classification using deep learning (LSTM and CNN) and natural language processing.

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

Google News and Leo Tolstoy: Visualizing Word2Vec Word Embeddings using t-SNE.

Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks

Sentiment Analysis: Deep Bi-LSTM+attention model

Molecular Explanation Generator

Implementation of Siamese CBOW using keras whose backend is tensorflow.

Named-Entity Recognition in Persian Language

Text processing library for sentiment analysis and related tasks

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

The code of our paper "SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model"

Data generator for Arena - interactive XAI dashboard

Code implementation for our ICPR, 2020 paper titled "Improving Word Recognition using Multiple Hypotheses and Deep Embeddings"

Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".

🍘 単語分割を経由しない単語埋め込み 🍘

Towards Understanding Deep Learning Representations via Interactive Experimentation

Sample code for training Word2Vec and FastText using wiki corpus and their pretrained word embedding..

💻Speech and Natural Language Processing (SLP & NLP) Lab Assignments for ECE NTUA

A little game powered by word vectors