bi-lstm-crf and Bert-BiLSTM-CRF-pytorch

These are competitors offering alternative architectural approaches to NER, with A using a classical BiLSTM-CRF baseline while B enhances it with BERT embeddings for improved contextual representation.

bi-lstm-crf
56
Established
Maintenance 0/25
Adoption 10/25
Maturity 25/25
Community 21/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Stars: 260
Forks: 46
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 283
Forks: 57
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
Stale 6m No Dependents
Stale 6m No Package No Dependents

About bi-lstm-crf

jidasheng/bi-lstm-crf

A PyTorch implementation of the BI-LSTM-CRF model.

This is a developer tool for building advanced natural language processing models. It helps machine learning engineers or data scientists create custom models for 'sequence tagging' tasks. You provide labeled text data as input, and it outputs a trained model that can identify and categorize specific elements within new text.

natural-language-processing sequence-tagging named-entity-recognition part-of-speech-tagging machine-learning-engineering

About Bert-BiLSTM-CRF-pytorch

cooscao/Bert-BiLSTM-CRF-pytorch

bert-bilstm-crf implemented in pytorch for named entity recognition.

This tool helps you automatically identify and extract specific types of entities, like names of people, places, or medical terms, from Chinese text. You input raw Chinese text that has been prepared into a specific 'BIO' format, and the system outputs the same text with the identified entities tagged. This is useful for anyone working with large volumes of Chinese text data, such as researchers, linguists, or data analysts.

Chinese-text-analysis information-extraction medical-data-processing linguistics data-annotation

Scores updated daily from GitHub, PyPI, and npm data. How scores work