MepropmeProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)
Stars: ✭ 90 (-94.73%)
Opus MtOpen neural machine translation models and web services
Stars: ✭ 111 (-93.5%)
Bible text gcnPytorch implementation of "Graph Convolutional Networks for Text Classification"
Stars: ✭ 90 (-94.73%)
ClicrMachine reading comprehension on clinical case reports
Stars: ✭ 123 (-92.8%)
Multiffn NliImplementation of the multi feed-forward network architecture by Parikh et al. (2016) for Natural Language Inference.
Stars: ✭ 89 (-94.79%)
Kaggle Freesound Audio Tagging8th place solution (on Kaggle) to the Freesound General-Purpose Audio Tagging Challenge (DCASE 2018 - Task 2)
Stars: ✭ 111 (-93.5%)
Virtual AssistantA linux based Virtual assistant on Artificial Intelligence in C
Stars: ✭ 88 (-94.85%)
Konoha🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.
Stars: ✭ 130 (-92.39%)
SpfCornell Semantic Parsing Framework
Stars: ✭ 87 (-94.91%)
Files2rougeCalculating ROUGE score between two files (line-by-line)
Stars: ✭ 120 (-92.97%)
MlA high-level machine learning and deep learning library for the PHP language.
Stars: ✭ 1,270 (-25.64%)
Kaggle CompetitionsThere are plenty of courses and tutorials that can help you learn machine learning from scratch but here in GitHub, I want to solve some Kaggle competitions as a comprehensive workflow with python packages. After reading, you can use this workflow to solve other real problems and use it as a template.
Stars: ✭ 86 (-94.96%)
TokenizerFast and customizable text tokenization library with BPE and SentencePiece support
Stars: ✭ 132 (-92.27%)
Practical OpenOxford Deep NLP 2017 course - Open practical
Stars: ✭ 84 (-95.08%)
KadotKadot, the unsupervised natural language processing library.
Stars: ✭ 108 (-93.68%)
Scanrefer[ECCV 2020] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
Stars: ✭ 84 (-95.08%)
Facial Expression RecognitionClassify each facial image into one of the seven facial emotion categories considered using CNN based on https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge
Stars: ✭ 82 (-95.2%)
PapernotesMy personal notes and surveys on DL, CV and NLP papers.
Stars: ✭ 108 (-93.68%)
Spacy Graphql🤹♀️ Query spaCy's linguistic annotations using GraphQL
Stars: ✭ 81 (-95.26%)
KaggleCode for Kaggle Competitions
Stars: ✭ 128 (-92.51%)
Opennmt TfNeural machine translation and sequence learning using TensorFlow
Stars: ✭ 1,223 (-28.4%)
Transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+3163.58%)
DialoglueDialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
Stars: ✭ 120 (-92.97%)
Practical 3 Oxford Deep NLP 2017 course - Practical 3: Text Classification with RNNs
Stars: ✭ 78 (-95.43%)
NltkNLTK Source
Stars: ✭ 10,309 (+503.57%)
Chinese XlnetPre-Trained Chinese XLNet(中文XLNet预训练模型)
Stars: ✭ 1,213 (-28.98%)
Rasa💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Stars: ✭ 13,219 (+673.95%)
Multimodal ToolkitMultimodal model for text and tabular data with HuggingFace transformers as building block for text data
Stars: ✭ 78 (-95.43%)
Dog Breeds ClassificationSet of scripts and data for reproducing dog breed classification model training, analysis, and inference.
Stars: ✭ 105 (-93.85%)
Dialogue UnderstandingThis repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study
Stars: ✭ 77 (-95.49%)
ScattertextBeautiful visualizations of how language differs among document types.
Stars: ✭ 1,722 (+0.82%)
Easy BertA Dead Simple BERT API for Python and Java (https://github.com/google-research/bert)
Stars: ✭ 106 (-93.79%)
RutermextractTerm extraction for Russian language
Stars: ✭ 75 (-95.61%)
MedquadMedical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites
Stars: ✭ 129 (-92.45%)
HunspellThe most popular spellchecking library.
Stars: ✭ 1,196 (-29.98%)
Ios mlList of Machine Learning, AI, NLP solutions for iOS. The most recent version of this article can be found on my blog.
Stars: ✭ 1,409 (-17.51%)
StminsightsA Shiny Application for Inspecting Structural Topic Models
Stars: ✭ 74 (-95.67%)
PymetamapPython wraper for MetaMap
Stars: ✭ 119 (-93.03%)
Nlp TutorialA list of NLP(Natural Language Processing) tutorials
Stars: ✭ 1,188 (-30.44%)
Spokestack PythonSpokestack is a library that allows a user to easily incorporate a voice interface into any Python application.
Stars: ✭ 103 (-93.97%)
Python nlp tutorialThis repository provides everything to get started with Python for Text Mining / Natural Language Processing (NLP)
Stars: ✭ 72 (-95.78%)
Scattertext PydataNotebooks for the Seattle PyData 2017 talk on Scattertext
Stars: ✭ 132 (-92.27%)
Absa PytorchAspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析,使用PyTorch实现。
Stars: ✭ 1,181 (-30.85%)
AnagoBidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.
Stars: ✭ 1,392 (-18.5%)
Allstate capstoneAllstate Kaggle Competition ML Capstone Project
Stars: ✭ 72 (-95.78%)
CryptoCryptocurrency Historical Market Data R Package
Stars: ✭ 112 (-93.44%)
ForteForte is a flexible and powerful NLP builder FOR TExt. This is part of the CASL project: http://casl-project.ai/
Stars: ✭ 89 (-94.79%)
MetaknowledgeA Python library for doing bibliometric and network analysis in science and health policy research
Stars: ✭ 102 (-94.03%)
NcrfppNCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+3.45%)
Sluice NetworksCode for Sluice networks: Learning what to share between loosely related tasks
Stars: ✭ 135 (-92.1%)
Zamia AiFree and open source A.I. system based on Python, TensorFlow and Prolog.
Stars: ✭ 133 (-92.21%)
TextacyNLP, before and after spaCy
Stars: ✭ 1,849 (+8.26%)