izhx/NER-unlabeled-data-retrieval
[COLING 22] Domain-Specific NER via Retrieving Correlated Samples.
This project helps natural language processing engineers efficiently develop systems that identify and extract specific types of information, like product names or address components, from unstructured text. It takes in raw, unlabeled text data relevant to a particular industry or context, and outputs a refined set of text samples that are most useful for training a specialized Named Entity Recognition (NER) model. NLP engineers who are building tailored information extraction systems for specific domains would use this.
No commits in the last 6 months.
Use this if you need to build a Named Entity Recognition model for a specific industry or data type, but have limited or no manually labeled training data available.
Not ideal if you already have a large, high-quality labeled dataset for your domain, or if you only need a general-purpose NER model.
Stars
23
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/izhx/NER-unlabeled-data-retrieval"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
charles9n/bert-sklearn
a sklearn wrapper for Google's BERT model
jidasheng/bi-lstm-crf
A PyTorch implementation of the BI-LSTM-CRF model.
howl-anderson/seq2annotation
基于 TensorFlow & PaddlePaddle 的通用序列标注算法库（目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和...
guillaumegenthial/tf_ner
Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data
guillaumegenthial/sequence_tagging
Named Entity Recognition (LSTM + CRF) - Tensorflow