Bert seq2seqpytorch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 (+292.11%)
Slot filling and intent detection of sluslot filling, intent detection, joint training, ATIS & SNIPS datasets, the Facebook’s multilingual dataset, MIT corpus, E-commerce Shopping Assistant (ECSA) dataset, CoNLL2003 NER, ELMo, BERT, XLNet
Stars: ✭ 298 (+292.11%)
Hscrf PytorchACL 2018: Hybrid semi-Markov CRF for Neural Sequence Labeling (http://aclweb.org/anthology/P18-2038)
Stars: ✭ 284 (+273.68%)
RnnsharpRNNSharp 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 (+264.47%)
keras-bert-nerKeras solution of Chinese NER task using BiLSTM-CRF/BiGRU-CRF/IDCNN-CRF model with Pretrained Language Model: supporting BERT/RoBERTa/ALBERT
Stars: ✭ 7 (-90.79%)
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 (-23.68%)
entity recognitionEntity recognition codes for "2019 Datagrand Cup: Text Information Extraction Challenge"
Stars: ✭ 26 (-65.79%)
grobid-nerA Named-Entity Recogniser based on Grobid.
Stars: ✭ 38 (-50%)
grobid-quantitiesGROBID extension for identifying and normalizing physical quantities.
Stars: ✭ 53 (-30.26%)
Computer-Visionimplemented some computer vision problems
Stars: ✭ 25 (-67.11%)
crfs-rsPure Rust port of CRFsuite: a fast implementation of Conditional Random Fields (CRFs)
Stars: ✭ 22 (-71.05%)
CIPBasic exercises of chinese information processing
Stars: ✭ 32 (-57.89%)
jcrfsuiteJava interface for CRFsuite: http://www.chokkan.org/software/crfsuite/
Stars: ✭ 44 (-42.11%)
crf4ja complete Java port of crfpp(crf++)
Stars: ✭ 30 (-60.53%)
crf-segcrf-seg:用于生产环境的中文分词处理工具,可自定义语料、可自定义模型、架构清晰,分词效果好。java编写。
Stars: ✭ 13 (-82.89%)