Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

Last update: Dec 26, 2022

Overview

For better performance, you can try NLPGNN, see NLPGNN for more details.

BERT-NER Version 2

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

The original version （see old_version for more detail） contains some hard codes and lacks corresponding annotations,which is inconvenient to understand. So in this updated version,there are some new ideas and tricks （On data Preprocessing and layer design） that can help you quickly implement the fine-tuning model (you just need to try to modify crf_layer or softmax_layer).

Folder Description:

BERT-NER
|____ bert                          # need git from [here](https://github.com/google-research/bert)
|____ cased_L-12_H-768_A-12	    # need download from [here](https://storage.googleapis.com/bert_models/2018_10_18/cased_L-12_H-768_A-12.zip)
|____ data		            # train data
|____ middle_data	            # middle data (label id map)
|____ output			    # output (final model, predict results)
|____ BERT_NER.py		    # mian code
|____ conlleval.pl		    # eval code
|____ run_ner.sh    		    # run model and eval result

Usage:

bash run_ner.sh

What's in run_ner.sh:

python BERT_NER.py\
    --task_name="NER"  \
    --do_lower_case=False \
    --crf=False \
    --do_train=True   \
    --do_eval=True   \
    --do_predict=True \
    --data_dir=data   \
    --vocab_file=cased_L-12_H-768_A-12/vocab.txt  \
    --bert_config_file=cased_L-12_H-768_A-12/bert_config.json \
    --init_checkpoint=cased_L-12_H-768_A-12/bert_model.ckpt   \
    --max_seq_length=128   \
    --train_batch_size=32   \
    --learning_rate=2e-5   \
    --num_train_epochs=3.0   \
    --output_dir=./output/result_dir

perl conlleval.pl -d '\t' < ./output/result_dir/label_test.txt

Notice: cased model was recommened, according to this paper. CoNLL-2003 dataset and perl Script comes from here

RESULTS:(On test set)

Parameter setting:

do_lower_case=False
num_train_epochs=4.0
crf=False

accuracy:  98.15%; precision:  90.61%; recall:  88.85%; FB1:  89.72
              LOC: precision:  91.93%; recall:  91.79%; FB1:  91.86  1387
             MISC: precision:  83.83%; recall:  78.43%; FB1:  81.04  668
              ORG: precision:  87.83%; recall:  85.18%; FB1:  86.48  1191
              PER: precision:  95.19%; recall:  94.83%; FB1:  95.01  1311

Result description:

Here i just use the default paramaters, but as Google's paper says a 0.2% error is reasonable(reported 92.4%). Maybe some tricks need to be added to the above model.

reference:

[1] https://arxiv.org/abs/1810.04805

[2] https://github.com/google-research/bert

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

Related tags

Overview

For better performance, you can try NLPGNN, see NLPGNN for more details.

BERT-NER Version 2

Folder Description:

Usage:

What's in run_ner.sh:

RESULTS:(On test set)

Parameter setting:

Result description:

reference:

Owner

Kaiyinzhou

Code for Findings at EMNLP 2021 paper: "Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning"

Unsupervised Language Modeling at scale for robust sentiment classification

A library for end-to-end learning of embedding index and retrieval model

Textpipe: clean and extract metadata from text

This Project is based on NLTK It generates a RANDOM WORD from a predefined list of words, From that random word it read out the word, its meaning with parts of speech , its antonyms, its synonyms

jiant is an NLP toolkit

iBOT: Image BERT Pre-Training with Online Tokenizer

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

Curso práctico: NLP de cero a cien 🤗

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

Natural Language Processing library built with AllenNLP 🌲🌱

使用pytorch+transformers复现了SimCSE论文中的有监督训练和无监督训练方法

The following links explain a bit the idea of semantic search and how search mechanisms work by doing retrieve and rerank

BMInf (Big Model Inference) is a low-resource inference package for large-scale pretrained language models (PLMs).

A linter to manage all your python exceptions and try/except blocks (limited only for those who like dinosaurs).

Repository for Project Insight: NLP as a Service

Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

NLP topic mdel LDA - Gathered from New York Times website

This is a project built for FALLABOUT2021 event under SRMMIC, This project deals with NLP poetry generation.

Translates basic English sentences into the Huna language (hoo-NAH)