datastories-semeval2017-task6Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Stars: ✭ 20 (-74.36%)
Datastories Semeval2017 Task4Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (+135.9%)
NTUA-slp-nlp💻Speech and Natural Language Processing (SLP & NLP) Lab Assignments for ECE NTUA
Stars: ✭ 19 (-75.64%)
word2vec-tsneGoogle News and Leo Tolstoy: Visualizing Word2Vec Word Embeddings using t-SNE.
Stars: ✭ 59 (-24.36%)
Deeplearning Nlp ModelsA 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.
Stars: ✭ 64 (-17.95%)
DeepehrChronic Disease Prediction Using Medical Notes
Stars: ✭ 220 (+182.05%)
SentimentAnalysisSentiment Analysis: Deep Bi-LSTM+attention model
Stars: ✭ 32 (-58.97%)
Contextualized Topic ModelsA 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.
Stars: ✭ 318 (+307.69%)
Entity EmbeddingReference implementation of the paper "Word Embeddings for Entity-annotated Texts"
Stars: ✭ 19 (-75.64%)
pfootprintPolitical Discourse Analysis Using Pre-Trained Word Vectors.
Stars: ✭ 20 (-74.36%)
presidential-rnnProject 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.
Stars: ✭ 26 (-66.67%)
Paribhashaparibhasha.herokuapp.com/
Stars: ✭ 21 (-73.08%)
event-embedding-multitask*SEM 2018: Learning Distributed Event Representations with a Multi-Task Approach
Stars: ✭ 22 (-71.79%)
awesome-yoruba-nlp📖 A curated list of resources dedicated to Natural Language Processing (NLP) in the Yoruba Language.
Stars: ✭ 21 (-73.08%)
lstm-attentionAttention-based bidirectional LSTM for Classification Task (ICASSP)
Stars: ✭ 87 (+11.54%)
simple elmoSimple library to work with pre-trained ELMo models in TensorFlow
Stars: ✭ 49 (-37.18%)
Catalyst🚀 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.
Stars: ✭ 224 (+187.18%)
Cw2veccw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information
Stars: ✭ 224 (+187.18%)
flow1d[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation
Stars: ✭ 91 (+16.67%)
bert attn vizVisualize BERT's self-attention layers on text classification tasks
Stars: ✭ 41 (-47.44%)
Magnetloss PytorchPyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016.
Stars: ✭ 217 (+178.21%)
word-embeddings-from-scratchCreating word embeddings from scratch and visualize them on TensorBoard. Using trained embeddings in Keras.
Stars: ✭ 22 (-71.79%)
PyEmbeograph embeddings for neo4j in python
Stars: ✭ 25 (-67.95%)
dreyeve[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.
Stars: ✭ 88 (+12.82%)
image embeddingsUsing efficientnet to provide embeddings for retrieval
Stars: ✭ 107 (+37.18%)
img2vec-kerasImage to dense vector embedding. Clone of https://github.com/christiansafka/img2vec for Keras users
Stars: ✭ 36 (-53.85%)
AiROfficial Repository for ECCV 2020 paper "AiR: Attention with Reasoning Capability"
Stars: ✭ 41 (-47.44%)
seq2seq-pytorchSequence to Sequence Models in PyTorch
Stars: ✭ 41 (-47.44%)
SumrizedAutomatic Text Summarization (English/Arabic).
Stars: ✭ 37 (-52.56%)
MGANExploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification (AAAI'19)
Stars: ✭ 44 (-43.59%)
keras-utility-layer-collectionCollection of custom layers and utility functions for Keras which are missing in the main framework.
Stars: ✭ 63 (-19.23%)
WhatliesToolkit to help understand "what lies" in word embeddings. Also benchmarking!
Stars: ✭ 246 (+215.38%)
natural-language-joint-query-searchSearch photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.
Stars: ✭ 143 (+83.33%)
tensorflow-chatbot-chinese網頁聊天機器人 | tensorflow implementation of seq2seq model with bahdanau attention and Word2Vec pretrained embedding
Stars: ✭ 50 (-35.9%)
KprnReasoning Over Knowledge Graph Paths for Recommendation
Stars: ✭ 220 (+182.05%)
empythyAutomated NLP sentiment predictions- batteries included, or use your own data
Stars: ✭ 17 (-78.21%)
CauseCode for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
Stars: ✭ 207 (+165.38%)
Im2LaTeXAn implementation of the Show, Attend and Tell paper in Tensorflow, for the OpenAI Im2LaTeX suggested problem
Stars: ✭ 16 (-79.49%)
SensegramMaking sense embedding out of word embeddings using graph-based word sense induction
Stars: ✭ 209 (+167.95%)
fake-newsThis is a further development of the kdnuggets article on fake news classification by George McIntyre
Stars: ✭ 15 (-80.77%)
VectoraiVector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.
Stars: ✭ 195 (+150%)
Research2vecRepresenting research papers as vectors / latent representations.
Stars: ✭ 192 (+146.15%)
query-wellformedness25,100 queries from the Paralex corpus (Fader et al., 2013) annotated with human ratings of whether they are well-formed natural language questions.
Stars: ✭ 80 (+2.56%)
ParallaxTool for interactive embeddings visualization
Stars: ✭ 192 (+146.15%)
scicle-stopclickbaitUserscript that changes Clickbait headlines by headlines more honest to the news it links to.
Stars: ✭ 16 (-79.49%)
NLP-Flask-WebsiteA simple Flask website for all NLP tasks which includes Text Preprocessing, Keyword Extraction, Text Summarization etc. Created Date: 30 Jan 2019
Stars: ✭ 43 (-44.87%)
attention-ocrA pytorch implementation of the attention based ocr
Stars: ✭ 44 (-43.59%)
Vec4irWord Embeddings for Information Retrieval
Stars: ✭ 188 (+141.03%)
JodieA PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
Stars: ✭ 172 (+120.51%)
geometric embedding"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation
Stars: ✭ 19 (-75.64%)
Cx db8a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
Stars: ✭ 164 (+110.26%)