All Projects → lonePatient → Daguan_2019_rank9

lonePatient / Daguan_2019_rank9

datagrand 2019 information extraction competition rank9

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Daguan 2019 rank9

Multilstm
keras attentional bi-LSTM-CRF for Joint NLU (slot-filling and intent detection) with ATIS
Stars: ✭ 122 (+0.83%)
Mutual labels:  lstm, ner, crf
Ner Lstm Crf
An easy-to-use named entity recognition (NER) toolkit, implemented the Bi-LSTM+CRF model in tensorflow.
Stars: ✭ 337 (+178.51%)
Mutual labels:  lstm, ner, crf
Ner blstm Crf
LSTM-CRF for NER with ConLL-2002 dataset
Stars: ✭ 51 (-57.85%)
Mutual labels:  lstm, ner, crf
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 (+1360.33%)
Mutual labels:  lstm, ner, crf
BiLSTM-CRF-NER-PyTorch
This repo contains a PyTorch implementation of a BiLSTM-CRF model for named entity recognition task.
Stars: ✭ 109 (-9.92%)
Mutual labels:  crf, lstm, ner
lstm-crf-tagging
No description or website provided.
Stars: ✭ 13 (-89.26%)
Mutual labels:  crf, lstm, ner
korean ner tagging challenge
KU_NERDY 이동엽, 임희석 (2017 국어 정보 처리 시스템경진대회 금상) - 한글 및 한국어 정보처리 학술대회
Stars: ✭ 30 (-75.21%)
Mutual labels:  crf, lstm, ner
knowledge-graph-nlp-in-action
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。
Stars: ✭ 58 (-52.07%)
Mutual labels:  crf, information-extraction, lstm
Lstms.pth
PyTorch implementations of LSTM Variants (Dropout + Layer Norm)
Stars: ✭ 111 (-8.26%)
Mutual labels:  lstm, dropout
Snips Nlu
Snips Python library to extract meaning from text
Stars: ✭ 3,583 (+2861.16%)
Mutual labels:  ner, information-extraction
Bert Ner Pytorch
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Stars: ✭ 654 (+440.5%)
Mutual labels:  ner, crf
Named entity recognition
中文命名实体识别(包括多种模型:HMM,CRF,BiLSTM,BiLSTM+CRF的具体实现)
Stars: ✭ 995 (+722.31%)
Mutual labels:  ner, crf
Macropodus
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(name entity recognition),Find(new words discovery),Keyword(keyword extraction),Summarize(text summarization),Sim(text similarity),Calculate(scientific calculator),Chi2num(chinese number to arabic number)
Stars: ✭ 309 (+155.37%)
Mutual labels:  ner, crf
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 (+3071.9%)
Mutual labels:  ner, crf
Theano lstm
🔬 Nano size Theano LSTM module
Stars: ✭ 310 (+156.2%)
Mutual labels:  lstm, dropout
Bert seq2seq
pytorch实现bert做seq2seq任务,使用unilm方案,现在也可以做自动摘要,文本分类,情感分析,NER,词性标注等任务,支持GPT2进行文章续写。
Stars: ✭ 298 (+146.28%)
Mutual labels:  ner, crf
Lm Lstm Crf
Empower Sequence Labeling with Task-Aware Language Model
Stars: ✭ 778 (+542.98%)
Mutual labels:  ner, crf
Ntagger
reference pytorch code for named entity tagging
Stars: ✭ 58 (-52.07%)
Mutual labels:  ner, crf
Chinese semantic role labeling
基于 Bi-LSTM 和 CRF 的中文语义角色标注
Stars: ✭ 60 (-50.41%)
Mutual labels:  lstm, crf
Tf Lstm Crf Batch
Tensorflow-LSTM-CRF tool for Named Entity Recognizer
Stars: ✭ 59 (-51.24%)
Mutual labels:  lstm, crf

datagrand_2019_rank9

2019年达观信息提取比赛第九名代码和答辩ppt

比赛地址:官网

代码目录结构

├── pydatagrand
|  └── callback
|  |  └── lrscheduler.py  
|  |  └── trainingmonitor.py 
|  |  └── ...
|  └── config
|  |  └── basic_config.py #a configuration file for storing model parameters
|  └── dataset   
|  └── io    
|  |  └── dataset.py  
|  |  └── data_transformer.py  
|  └── model
|  |  └── nn 
|  |  └── pretrain 
|  └── output #save the ouput of model
|  └── preprocessing #text preprocessing 
|  └── train #used for training a model
|  |  └── trainer.py 
|  |  └── ...
|  └── common # a set of utility functions
├── prepare_fold_data.py  # 数据切分
├── prepare_lm_data_mask.py  # 随机mask
├── prepare_lm_data_ngram.py  #ngram mask
├── run_bert_crf.py        # crf结构
├── run_bert_span.py   # span结构
├── train_bert_model.py  #训练bert模型

预训练模型

主要训练了8层跟12层BERT模型,采用随机mask + ngram mask两种混合动态masking模式

方案1

方案1主要采用BERT+LSTM+CRF结构

方案2

方案2在方案1的基础上增加了MDP结构

方案3

方案3主要采用BERT+LSTM+SPAN结构

结果

最终结果如下所示:

文档

十强答辩ppt下载地址: https://pan.baidu.com/s/1yvXFf5GzyvDksdBKNp9FKQ 提取码: svr2

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].