GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → saiwaiyanyu → knowledge-graph-nlp-in-action

saiwaiyanyu / knowledge-graph-nlp-in-action

Licence: other
从模型训练到部署，实战知识图谱(Knowledge Graph)&自然语言处理(NLP)。涉及 Tensorflow, Bert+Bi-LSTM+CRF,Neo4j等 涵盖 Named Entity Recognition,Text Classify,Information Extraction,Relation Extraction 等任务。

Programming Languages

python
139335 projects - #7 most used programming language
Jupyter Notebook
11667 projects

Labels

nlpneo4jtensorflowcrfinformation-extractionknowledge-graphlstmnamed-entity-recognitionbertrelation-extraction

Projects that are alternatives of or similar to knowledge-graph-nlp-in-action

Tf Lstm Crf Batch
Tensorflow-LSTM-CRF tool for Named Entity Recognizer
Stars: ✭ 59 (+1.72%)
Mutual labels:  crf, lstm, named-entity-recognition
Ncrfpp
NCRF++, 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 (+2946.55%)
Mutual labels:  crf, lstm, named-entity-recognition
End To End Sequence Labeling Via Bi Directional Lstm Cnns Crf Tutorial
Tutorial for End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Stars: ✭ 87 (+50%)
Mutual labels:  crf, lstm, named-entity-recognition
Information Extraction Chinese
Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取
Stars: ✭ 1,888 (+3155.17%)
Mutual labels:  information-extraction, named-entity-recognition, relation-extraction
CogIE
CogIE: An Information Extraction Toolkit for Bridging Text and CogNet. ACL 2021
Stars: ✭ 47 (-18.97%)
Mutual labels:  information-extraction, named-entity-recognition, relation-extraction
Bert Bilstm Crf Ner
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Stars: ✭ 3,838 (+6517.24%)
Mutual labels:  crf, named-entity-recognition, bert
Multilstm
keras attentional bi-LSTM-CRF for Joint NLU (slot-filling and intent detection) with ATIS
Stars: ✭ 122 (+110.34%)
Mutual labels:  crf, lstm, named-entity-recognition
Daguan 2019 rank9
datagrand 2019 information extraction competition rank9
Stars: ✭ 121 (+108.62%)
Mutual labels:  crf, information-extraction, lstm
IE Paper Notes
Paper notes for Information Extraction, including Relation Extraction (RE), Named Entity Recognition (NER), Entity Linking (EL), Event Extraction (EE), Named Entity Disambiguation (NED).
Stars: ✭ 14 (-75.86%)
Mutual labels:  information-extraction, named-entity-recognition, relation-extraction
lima
The Libre Multilingual Analyzer, a Natural Language Processing (NLP) C++ toolkit.
Stars: ✭ 75 (+29.31%)
Mutual labels:  information-extraction, named-entity-recognition, relation-extraction
Casrel
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction. Accepted by ACL 2020.
Stars: ✭ 329 (+467.24%)
Mutual labels:  information-extraction, knowledge-graph, relation-extraction
Shukongdashi
使用知识图谱，自然语言处理，卷积神经网络等技术，基于python语言，设计了一个数控领域故障诊断专家系统
Stars: ✭ 109 (+87.93%)
Mutual labels:  knowledge-graph, named-entity-recognition, relation-extraction
Agriculture knowledgegraph
农业知识图谱(AgriKG)：农业领域的信息检索，命名实体识别，关系抽取，智能问答，辅助决策
Stars: ✭ 2,957 (+4998.28%)
Mutual labels:  knowledge-graph, named-entity-recognition, relation-extraction
Ner blstm Crf
LSTM-CRF for NER with ConLL-2002 dataset
Stars: ✭ 51 (-12.07%)
Mutual labels:  crf, lstm, named-entity-recognition
OpenUE
OpenUE是一个轻量级知识图谱抽取工具 (An Open Toolkit for Universal Extraction from Text published at EMNLP2020: https://aclanthology.org/2020.emnlp-demos.1.pdf)
Stars: ✭ 274 (+372.41%)
Mutual labels:  named-entity-recognition, bert, relation-extraction
korean ner tagging challenge
KU_NERDY 이동엽, 임희석 (2017 국어 정보 처리 시스템경진대회 금상) - 한글 및 한국어 정보처리 학술대회
Stars: ✭ 30 (-48.28%)
Mutual labels:  crf, lstm, named-entity-recognition
InformationExtractionSystem
Information Extraction System can perform NLP tasks like Named Entity Recognition, Sentence Simplification, Relation Extraction etc.
Stars: ✭ 27 (-53.45%)
Mutual labels:  information-extraction, named-entity-recognition, relation-extraction
FDDC
Named Entity Recognition & Relation Extraction 实体命名识别与关系分类
Stars: ✭ 29 (-50%)
Mutual labels:  named-entity-recognition, relation-extraction
KGPool
[ACL 2021] KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
Stars: ✭ 33 (-43.1%)
Mutual labels:  knowledge-graph, relation-extraction
simple NER
simple rule based named entity recognition
Stars: ✭ 29 (-50%)
Mutual labels:  information-extraction, named-entity-recognition
View All Similar Projects ➔

knowledge-graph-nlp-in-action

实战知识图谱和nlp相关任务，包括模型训练到部署全流程。

目录

NLP

sequence labeling

模型： Bert + BiLSTM + CRF

模型输入： 一段文本。

模型输出： 文本包含的机构、人名、时间等实体。

input text : 中共中央总书记、国家主席江泽民发表１９９８年新年讲话
[
    {
        "end": 4,
        "words": "中共中央",
        "type": "ORG",
        "begin": 1
    },
    {
        "end": 15,
        "words": "江泽民",
        "type": "PER",
        "begin": 13
    },
    {
        "end": 22,
        "words": "１９９８年",
        "type": "TIME",
        "begin": 18
    }
]

information extraction

模型： Bert

模型输入： 实体A，实体B，包含实体A和实体B的文本。

模型输出： 文本包含的机构、人名、时间等实体。

input: 喜剧之王      周星驰  如何演好自己的角色，请读《演员自我修养》《喜剧之王》周星驰崛起于穷困潦倒之中的独门秘笈

model version 1573956875

text: 喜剧之王  周星驰  如何演好自己的角色，请读《演员自我修养》《喜剧之王》周星驰崛起于穷困潦倒之中的独门秘笈
result:
{
    "主演": 0.9959173798561096,
    "导演": 0.0018050138605758548,
    "编剧": 0.000452475156635046,
    "歌手": 0.0002099768607877195,
    "制片人": 0.0001938332716235891,
    ...
}

***** Eval results ***** eval_accuracy = 0.97999 eval_loss = 0.06774125 global_step = 19000 loss = 0.06772543

seq2seq

模型： seq2seq greedy （QA）

模型输入： 输入你的梦境。

模型输出： 返回梦境解析的结果（周公解梦数据训练）。

********************
input your dream: 梦见中奖了
dream: 梦见中奖了
dream decoding: 预示你事业上将面临挑战和机遇，会有大发展。 

********************
input your dream: 梦见大富豪
dream: 梦见大富豪
dream decoding: 预示着自己生活会很愉快。

相关文档

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].