479 Open source projects that are alternatives of or similar to DeepLearningReading

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

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

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

Intelligent Word Embeddings of Free-Text Radiology Reports

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

📚 Text classification library with Keras

BertQA - Attention on Steroids

A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.

Chronic Disease Prediction Using Medical Notes

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

Sentiment Analysis: Deep Bi-LSTM+attention model

A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.

Reference implementation of the paper "Word Embeddings for Entity-annotated Texts"

Political Discourse Analysis Using Pre-Trained Word Vectors.

Keras implementation for CrossNet in paper "Cross-Target Stance Classification with Self-Attention Networks"

Project 4 for Metis bootcamp. Objective was generation of character-level RNN trained on Donald Trump's statements using Keras. Also generated Markov chains, and quick pyTorch RNN as baseline. Attempted semi-supervised GAN, but was unable to test in time.

paribhasha.herokuapp.com/

*SEM 2018: Learning Distributed Event Representations with a Multi-Task Approach

📖 A curated list of resources dedicated to Natural Language Processing (NLP) in the Yoruba Language.

Attention-based bidirectional LSTM for Classification Task (ICASSP)

Simple library to work with pre-trained ELMo models in TensorFlow

Probabilistic Dialogue Act Classification for the Switchboard Corpus using an LSTM model

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

Visualize BERT's self-attention layers on text classification tasks

A pytorch implementation of https://arxiv.org/abs/1904.09925

PyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016.

Creating word embeddings from scratch and visualize them on TensorBoard. Using trained embeddings in Keras.

graph embeddings for neo4j in python

[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.

Using efficientnet to provide embeddings for retrieval

Image to dense vector embedding. Clone of https://github.com/christiansafka/img2vec for Keras users

Official Repository for ECCV 2020 paper "AiR: Attention with Reasoning Capability"

Sequence to Sequence Models in PyTorch

Automatic Text Summarization (English/Arabic).

Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification (AAAI'19)

Collection of custom layers and utility functions for Keras which are missing in the main framework.

Toolkit to help understand "what lies" in word embeddings. Also benchmarking!

Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.

網頁聊天機器人 | tensorflow implementation of seq2seq model with bahdanau attention and Word2Vec pretrained embedding

Reasoning Over Knowledge Graph Paths for Recommendation

Automated NLP sentiment predictions- batteries included, or use your own data

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

An implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem

Making sense embedding out of word embeddings using graph-based word sense induction

🍔

This is a further development of the kdnuggets article on fake news classification by George McIntyre

seq2seq attention tensorflow textrank context

Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

Representing research papers as vectors / latent representations.

25,100 queries from the Paralex corpus (Fader et al., 2013) annotated with human ratings of whether they are well-formed natural language questions.

Tool for interactive embeddings visualization

Userscript that changes Clickbait headlines by headlines more honest to the news it links to.

A simple Flask website for all NLP tasks which includes Text Preprocessing, Keyword Extraction, Text Summarization etc. Created Date: 30 Jan 2019

A pytorch implementation of the attention based ocr

Word Embeddings for Information Retrieval

A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"

"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation

a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)