ZhixiuYe / Hscrf Pytorch
ACL 2018: Hybrid semi-Markov CRF for Neural Sequence Labeling (http://aclweb.org/anthology/P18-2038)
Stars: ✭ 284
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Hscrf Pytorch
Pytorch ner bilstm cnn crf
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF implement in pyotrch
Stars: ✭ 249 (-12.32%)
Mutual labels: ner, crf, sequence-labeling
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 (+250.35%)
Mutual labels: ner, crf, sequence-labeling
Ntagger
reference pytorch code for named entity tagging
Stars: ✭ 58 (-79.58%)
Mutual labels: ner, crf, sequence-labeling
Lm Lstm Crf
Empower Sequence Labeling with Task-Aware Language Model
Stars: ✭ 778 (+173.94%)
Mutual labels: ner, crf, sequence-labeling
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 (+522.18%)
Mutual labels: ner, crf, sequence-labeling
Kashgari
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
Stars: ✭ 2,235 (+686.97%)
Mutual labels: ner, sequence-labeling
A Pytorch Tutorial To Sequence Labeling
Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling
Stars: ✭ 257 (-9.51%)
Mutual labels: crf, sequence-labeling
BiLSTM-CRF-NER-PyTorch
This repo contains a PyTorch implementation of a BiLSTM-CRF model for named entity recognition task.
Stars: ✭ 109 (-61.62%)
Mutual labels: crf, ner
fairseq-tagging
a Fairseq fork for sequence tagging/labeling tasks
Stars: ✭ 26 (-90.85%)
Mutual labels: ner, sequence-labeling
Sequence tagging
Named Entity Recognition (LSTM + CRF) - Tensorflow
Stars: ✭ 1,889 (+565.14%)
Mutual labels: ner, crf
Pytorch Bert Crf Ner
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Stars: ✭ 236 (-16.9%)
Mutual labels: ner, crf
Ner Slot filling
中文自然语言的实体抽取和意图识别（Natural Language Understanding），可选Bi-LSTM + CRF 或者 IDCNN + CRF
Stars: ✭ 151 (-46.83%)
Mutual labels: ner, crf
korean ner tagging challenge
KU_NERDY 이동엽, 임희석 (2017 국어 정보 처리 시스템경진대회 금상) - 한글 및 한국어 정보처리 학술대회
Stars: ✭ 30 (-89.44%)
Mutual labels: crf, ner
deepseg
Chinese word segmentation in tensorflow 2.x
Stars: ✭ 23 (-91.9%)
Mutual labels: crf, sequence-labeling
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 (-97.54%)
Mutual labels: crf, ner
Hybrid semi-Markov CRF
HSCRF achieves F1 score of 91.38+/-0.10 on the CoNLL 2003 NER dataset, without using any additional corpus or resource.
Installation
PyTorch
The code is based on PyTorch. You can find installation instructions here.
Dependencies
The code is written in Python 2.7 and pytorch 0.2.0. Its dependencies are summarized in the file requirements.txt. You can install these dependencies like this:
pip install -r requirements.txt
Code reference
Usage
CUDA_VISIBLE_DEVICES=0 python train.py --char_lstm --high_way
word embeddings
Glove: You can find the pre-trained word embedding here,
and place glove.6B.100d.txt in data/.
Cite
If you use the code, please cite the following paper: "Hybrid semi-Markov CRF for Neural Sequence Labeling" Zhi-Xiu Ye, Zhen-Hua Ling. ACL (2018)
@InProceedings{HSCRF,
author = "Ye, Zhixiu
and Ling, Zhen-Hua",
title = "Hybrid semi-Markov CRF for Neural Sequence Labeling",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
year = "2018",
publisher = "Association for Computational Linguistics",
pages = "235--240",
location = "Melbourne, Australia",
url = "http://aclweb.org/anthology/P18-2038"
}
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].