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 → liu-nlper → Ner Lstm Crf

liu-nlper / Ner Lstm Crf

An easy-to-use named entity recognition (NER) toolkit, implemented the Bi-LSTM+CRF model in tensorflow.

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowdeeplearninglstmnercrf

Projects that are alternatives of or similar to Ner Lstm Crf

Ner blstm Crf
LSTM-CRF for NER with ConLL-2002 dataset
Stars: ✭ 51 (-84.87%)
Mutual labels:  lstm, ner, crf
korean ner tagging challenge
KU_NERDY 이동엽, 임희석 (2017 국어 정보 처리 시스템경진대회 금상) - 한글 및 한국어 정보처리 학술대회
Stars: ✭ 30 (-91.1%)
Mutual labels:  crf, lstm, ner
Multilstm
keras attentional bi-LSTM-CRF for Joint NLU (slot-filling and intent detection) with ATIS
Stars: ✭ 122 (-63.8%)
Mutual labels:  lstm, ner, crf
lstm-crf-tagging
No description or website provided.
Stars: ✭ 13 (-96.14%)
Mutual labels:  crf, lstm, ner
Daguan 2019 rank9
datagrand 2019 information extraction competition rank9
Stars: ✭ 121 (-64.09%)
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 (+424.33%)
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 (-67.66%)
Mutual labels:  crf, lstm, ner
OCR
Optical character recognition Using Deep Learning
Stars: ✭ 25 (-92.58%)
Mutual labels:  lstm, deeplearning
SentimentAnalysis
Sentiment Analysis: Deep Bi-LSTM+attention model
Stars: ✭ 32 (-90.5%)
Mutual labels:  lstm, deeplearning
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 (-11.57%)
Mutual labels:  ner, crf
deep-improvisation
Easy-to-use Deep LSTM Neural Network to generate song sounds like containing improvisation.
Stars: ✭ 53 (-84.27%)
Mutual labels:  lstm, deeplearning
Legal-Entity-Recognition
A Dataset of German Legal Documents for Named Entity Recognition
Stars: ✭ 98 (-70.92%)
Mutual labels:  crf, ner
battery-rul-estimation
Remaining Useful Life (RUL) estimation of Lithium-ion batteries using deep LSTMs
Stars: ✭ 25 (-92.58%)
Mutual labels:  lstm, deeplearning
Forecasting-Solar-Energy
Forecasting Solar Power: Analysis of using a LSTM Neural Network
Stars: ✭ 23 (-93.18%)
Mutual labels:  lstm, deeplearning
air writing
Online Hand Writing Recognition using BLSTM
Stars: ✭ 26 (-92.28%)
Mutual labels:  lstm, deeplearning
Learning-Lab-C-Library
This library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated
Stars: ✭ 20 (-94.07%)
Mutual labels:  lstm, deeplearning
Hierarchical-Word-Sense-Disambiguation-using-WordNet-Senses
Word Sense Disambiguation using Word Specific models, All word models and Hierarchical models in Tensorflow
Stars: ✭ 33 (-90.21%)
Mutual labels:  crf, lstm
Deeplearning.ai Assignments
Stars: ✭ 268 (-20.47%)
Mutual labels:  deeplearning, lstm
keras-bert-ner
Keras solution of Chinese NER task using BiLSTM-CRF/BiGRU-CRF/IDCNN-CRF model with Pretrained Language Model: supporting BERT/RoBERTa/ALBERT
Stars: ✭ 7 (-97.92%)
Mutual labels:  crf, ner
Rnnsharp
RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.
Stars: ✭ 277 (-17.8%)
Mutual labels:  lstm, crf
View All Similar Projects ➔

NER-LSTM-CRF

An easy-to-use named entity recognition (NER) toolkit, implemented the LSTM+[CNN]+CRF model in tensorflow.

该项目短期内不再维护，PyTorch版本：https://github.com/liu-nlper/SLTK

1. Model

Bi-LSTM/Bi-GRU + [CNN] + CRF，其中CNN层针对英文，捕获字符层面特征，通过参数use_char_feature控制self.nil_vars.add(self.feature_weight_dict[feature_name].name)。

2. Usage

2.1 数据准备

训练数据处理成下列形式，特征之间用制表符(或空格)隔开，每行共n列，1至n-1列为特征，最后一列为label。

苏   NR   B-ORG
州   NR   I-ORG
大   NN   I-ORG
学   NN   E-ORG
位   VV   O
于   VV   O
江   NR   B-GPE
苏   NR   I-GPE
省   NR   E-GPE
苏   NR   B-GPE
州   NR   I-GPE
市   NR   E-GPE

2.2 修改配置文件

Step 1: 将上述训练文件的路径写入配置文件config.yml中的data_params/path_train参数里；

Step 2: 以上样例数据中每行包含三列，分别称为f1、f2和label，首先需要将需要将model_params/feature_names设置为['f1', 'f2']，并将embed_params下的名称改为相应的feature name，其中的shape参数需要通过预处理之后才能得到(Step 3)，path_pre_train为预训练的词向量路径，格式同gensim生成的txt文件格式；

Step 3: 修改data_params下的参数：该参数存放特征和label的voc(即名称到编号id的映射字典)，改为相应的路径。

注：处理中文时，将char_feature参数设为false；处理英文时，设为true。

2.3 预处理

$ python/python3 preprocessing.py

预处理后，会得到各个特征的item数以及label数，并自动修改config.yml文件中各个feature的shape参数，以及nb_classes参数；

句子的最大长度参数sequence_length由参数sequence_len_pt控制，默认为98，即计算所得的句子长度sequence_length覆盖了98%的实例，可根据实际情况作调整；

需要注意的是，若提供了预训练的embedding向量，则特征embedding的维度以预训练的向量维度为准，若没有提供预训练的向量，则第一列的特征向量维度默认为64，其余特征为32，这里可以根据实际情况进行调整。

2.４ 训练模型

训练模型：根据需要调整其余参数，其中dev_size表示开发集占训练集的比例（默认值为0.1），并运行：

$ python/python3 train.py

2.５ 标记数据

标记数据：config.yml中修改相应的path_test和path_result，并运行：

$ python/python3 test.py

2.6 参数说明

参数 说明
1 rnn_unit str，['lstm', 'gru']，模型中使用哪种单元，用户设置，默认值lstm
2 num_units int，bilstm/bigru单元数，用户设置，默认值256
3 num_layers int，bilstm/bigru层数，用户设置，默认值1
4 rnn_dropout float，lstm/gru层的dropout值，用户设置，默认值0.2
5 use_crf bool，是否使用crf层，用户设置，默认值true
6 use_char_feature bool，是否使用字符层面特征（针对英文），用户设置，默认值false
7 learning_rate float，学习率，用户设置，默认值0.001
8 dropout_rate float，bilstm/bigru输出与全连接层之间，用户设置，默认值0.5
9 l2_rate float，加在全连接层权重上，用户设置，默认值0.001
10 clip: None or int, 梯度裁剪，用户设置，默认值10
11 dev_size float between (0, 1)，训练集中划分出的开发集的比例，shuffle之后再划分，用户设置，默认值0.2
12 sequence_len_pt int，句子长度百分数，用于设定句子最大长度，用户设置，默认值98
13 sequence_length int，句子最大长度，由参数sequence_len_pt计算出，无需设置
14 word_len_pt int，单词长度百分数，用于设定单词最大长度，只有在use_char_feature设为true时才会使用，用户设置，默认值95
15 word_length int，单词最大长度，由参数word_len_pt计算出
16 nb_classes int，标签数，自动计算，无需设置
17 batch_size int，batch size，用户设置，默认值为64
18 nb_epoch int，迭代次数，用户设置
19 max_patience int，最大耐心值，即在开发集上的表现累计max_patience次没有提升时，训练即终止，用户设置，默认值5
20 path_model str，模型存放路径，用户设置，默认值值./Model/best_model
21 sep str，['table', 'space']，表示特征之间的分隔符，用户设置，默认值table
22 conv_filter_size_list list，当使用char feature时，卷积核的数量，用户设定，默认值[8, 8, 8, 8, 8]
23 conv_filter_len_list list，当使用char feature时，卷积核的尺寸，用户设定，默认值[1, 2, 3, 4, 5]
24 conv_dropout 卷积层的dropout rate
25 Other parameters ......

3. Utils

一些小工具，包括：

  • train_word2vec_model.py: 利用gensim训练词向量；
  • trietree.py: 构建Trie树，并实现查找（待优化），可用于构建字典特征；
  • KeywordExtractor，trietree.py用KeywordExtractor库代替，提供更多接口；
  • updating...

4. Requirements

  • numpy
  • tensorflow 1.4
  • pickle
  • tqdm
  • yaml

5. References

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].