a101269 Goto Github PK

hanlp

自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁

hanzi_char_featurizer

汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征

hpyp

Implementation of Hierarchical Pitman Yor processes

ijcai2019-dp-sa

The implementation of "Self-attentive Biaffine Dependency Parsing"

interface-demo-of-producer-consumer-problem

A dynamics Demonstration

k-bert

Source code of K-BERT

kptimes

Repository for KPTimes corpus

latticelstm

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

lda

LDA主题分类模型

lda_gibbs_sampling

a python implementation of latent dirichlet allocation(lda) using gibbs sampling algorithm

lda_variational_em

a python implementation of latent dirichlet allocation(lda) using variational EM algorithm

lstm-sdparser

LSTM-based dependency graph parser with Bi-LSTM Subtraction and Incremental Tree-LSTM

models

Models and examples built with TensorFlow

mpywe

Morpheme, Pinyin Enhanced Word Embedding

multi-grained-ner

multiple-relations-extraction-only-look-once

Multiple-Relations-Extraction-Only-Look-Once. Just look at the sentence once and extract the multiple pairs of entities and their corresponding relations. 端到端联合多关系抽取模型，可用于 http://lic2019.ccf.org.cn/kg 信息抽取。

ner-bert-pytorch

PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.

nested-ner-2019-bert

Implementation of Nested Named Entity Recognition using BERT

nlp-datasets

Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)

openke

An Open-Source Package for Knowledge Embedding (KE)

p-tuning

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

paddlenlp

Easy-to-use and Fast NLP library with awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications.

parser-v3

Stanford CoNLL 2018 Graph-based Dependency Parser

pattern-exploiting-training

Pattern-Exploiting Training在中文上的简单实验

pegasus

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

phrase-pinyin-data

词语拼音数据

phraseextractor

phrasemining

Phrase mining by weak supervised learning, only a little tagged data, Divide phrases into nonsense and good ones

pytorch_tutorial

《Pytorch模型训练实用教程》中配套代码