9 results found Sort:

ownthink
Jiagu ownthink
612
3.2k
mit
86
Jiagu深度学习自然语言处理工具 知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类
cws ner nlp pos chinese-word-segmentation
Created 2018-12-30
107 commits to master branch, last one 2 years ago
sn4k3
UVtools sn4k3
102
1.1k
agpl-3.0
33
MSLA/DLP, file analysis, calibration, repair, conversion and manipulation
ctb cws dlp phz pws zip mesh msla slice cbddlp photon viewer analysis prusa-sl1 convertion 3d-printing prusaslicer resin-printer 3d-reconstruction resin-3d-printers
Created 2020-04-05
1,255 commits to master branch, last one 2 months ago
smilelight
lightNLP smilelight
212
824
apache-2.0
31
基于Pytorch和torchtext的自然语言处理深度学习框架。
cws nlp pos srl cbow python chinese pytorch word2vec skip-gram torchtext deep-learning language-model negative-sampling dependency-parsing relation-extraction sentence-similarity text-classification hierarchical-softmax nature-language-process
Created 2019-01-25
73 commits to master branch, last one 3 years ago
fastnlp
fastHan fastnlp
86
744
apache-2.0
21
fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具，像spacy一样调用方便。
cws ner pos bert parser python fastnlp pytorch joint-model
Created 2019-10-23
69 commits to master branch, last one 6 months ago
yongzhuo
Macropodus yongzhuo
94
649
mit
14
自然语言处理工具Macropodus，基于Albert+BiLSTM+CRF深度学习网络架构，中文分词，词性标注，命名实体识别，新词发现，关键词，文本摘要，文本相似度，科学计算器，中文数字阿拉伯数字(罗马数字)转换，中文繁简转换，拼音转换。tookit(tool) of NLP，CWS(chinese word segnment)，POS(Part-Of-Speech Tagging)，NER(n...
crf cws ner nlp albert keyword newword segnment calulator macropodus similarity text-summarization
Created 2019-12-31
17 commits to master branch, last one 3 years ago
JayYip
m3tl JayYip
126
544
apache-2.0
19
BERT for Multitask Learning
cws ner nlp bert transformer part-of-speech encoder-decoder pretrained-models word-segmentation multitask-learning multi-task-learning text-classification named-entity-recognition
Created 2018-11-29
535 commits to master branch, last one about a year ago
Droidtown
ArticutAPI Droidtown
35
405
mit
13
API of Articut 中文斷詞 (兼具語意詞性標記)：「斷詞」又稱「分詞」，是中文資訊處理的基礎。Articut 不用機器學習，不需資料模型，只用現代白話中文語法規則，即能達到 SIGHAN 2005 F1-measure 94% 以上，Recall 96% 以上的成績。
cws nlp nlu pos-tagger pos-tagging part-of-speech-tagger artificial-intelligence part-of-speech-embdding natural-language-processing natural-language-understanding
Created 2019-04-26
426 commits to master branch, last one 5 months ago
hankcs
ID-CNN-CWS hankcs
40
136
gpl-3.0
10
Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"
cnn crf cws nlp bilstm tensorflow
Created 2017-10-20
10 commits to master branch, last one 3 years ago
PaloAltoNetworks
prisma_channel_resources PaloAltoNetworks
54
62
mit
15
A collection of technical and sales resources related to Prisma Cloud Compute and Prisma Cloud Enterprise created for the PANW Channel Partner Ecosystem and other engineers working with the solution
cwp cws cspm cnapp prisma aporeto redlock devsecops twistlock prisma-cloud containersecurity cloudnativesecurity
Created 2021-11-09
843 commits to main branch, last one 13 days ago