Named Entity Recognition Ner
Named Entity Recognition (NER) is a task in Natural Language Processing (NLP) aimed at identifying and classifying named entities in text into predefined categories such as person names, organizations, locations, etc. Its goal is to extract structured information from unstructured text data and represent it in a machine-readable format. NER has significant application value in areas like information retrieval, knowledge graph construction, sentiment analysis, and typically employs the BIO tagging scheme to distinguish the beginning and inside of entity markings.
BINDER
ACE + document-context
LUKE + SubRegWeigh (K-means)
KeBioLM
BERT-MRC+DSC
SciDeBERTa v2
UNER XML-R
BiLSTM-CRF with ELMo
Ours: cross-sentence ALB
Ours: cross-sentence ALB
DeepStruct multi-task w/ finetune
BLSTM-CNN-Char (SparkNLP)
BioLinkBERT (large)
BertForTokenClassification (Spark NLP)
SciFive-Large
BioMegatron
BLSTM-CNN-Char (SparkNLP)
PubMedBERT-CRF
MacBERT-large
HME (word + BPE + char)
LUKE(Large)
SWEM-CRF
ACE
FLERT XLM-R
LS-unLLaMA
PL-Marker
BiLSTM-CRF
ConNER
cfilt/HiNER-original-xlm-roberta-large
BiLSTM with ELMo
XLM-RoBERTa
Marcell
LSTM-CRF
BLSTM-CNN-Char (SparkNLP)
BERT
UniNER-7B
AlephBERT-base
HGN
FT-Bangla BERT Large
W2V2-L-LL60K (pipeline approach, uses LM)
SciFive-Base
BLSTM-CNN-Char (SparkNLP)
DyGIE
mgsohrab
HGN
CL-KL