dingyunxia Goto Github PK

abusive-language

algorithm_interview_notes-chinese

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

alw3-acl2019

Pay "Attention'' to your Context when Classifying Abusive Language

an-attentive-neural-model-for-labeling-adverse-drug-reactions

An Attentive Neural Sequence Labeling Model for Adverse Drug Reactions Mentions Extraction

an-ensemble-of-attention-based-bilstm-model-for-machine-comprehension

An implementation for SemEval 2018 Task 11: Machine Comprehension using Commonsense Knowledge

anago

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

ark-twokenize-py

Python port of the Twokenize class of ark-tweet-nlp

bert

TensorFlow code and pre-trained models for BERT

bert-as-service

Mapping a variable-length sentence to a fixed-length vector using pretrained BERT model

bert4keras

Our light reimplement of bert for keras

bible_text_gcn

Pytorch implementation of "Graph Convolutional Networks for Text Classification"

capsule-text-classification

利用keras搭建的胶囊网络（capsule network文本分类模型，包含RNN、CNN、HAN等，其中keras_utils包含了capsule层和attention层的keras实现

cdcs

Chinese Data Competitions' Solutions

char-embeddings

A repository containing 300D character embeddings derived from the GloVe 840B/300D dataset, and uses these embeddings to train a deep learning model to generate Magic: The Gathering cards using Keras

char-tsne-visualization

Visualizations of character embeddings from derived character vectors.

classification-of-hate-speech-and-abusive-language-based-on-attention-selection-mechanism-with-multi

The paper "Classification of hate speech and abusive language based on attention selection mechanism with multi-granularity embedding(MGE) " coed

cose

The code for contextual sentiment embeddings

ekphrasis

Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

fasttext

Library for fast text representation and classification.

hate-speech

Source code of the experiment documented in: Pitsilis G.K, Ramampiaro, H., Langseth, H., “Detecting Offensive Language in Tweets Using Deep Learning”, 2018/1/13, arXiv preprint arXiv:1801.04433.

hate-speech-and-offensive-language

Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017

hatespeech

keras-indrnn

Implementation of IndRNN in Keras

keras-sru

Implementation of Simple Recurrent Unit in Keras

keras-targeted-dropout

Targeted dropout implemented in Keras

keras-textclassification

中文长文本分类、短句子分类、多标签分类（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, ENT, DMN,

machinelearning

My blogs and code for machine learning. http://cnblogs.com/pinard

ml-tutorial-experiment

Coding the Machine Learning Tutorial for Learning to Learn

nndl.github.io

《神经网络与深度学习》 Neural Network and Deep Learning

non-discrimination-learning-for-text-classification

This is the code in <Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting> which has been accepted by ACL 2020