entity_recognition
entity_recognition copied to clipboard
framework for doing NER and other types of entity recognition, in Python
Bumps [numpy](https://github.com/numpy/numpy) from 1.10.4 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
Bumps [nltk](http://nltk.org/) from 3.2 to 3.4.5. [](https://help.github.com/articles/configuring-automated-security-fixes) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a...
Tensorflow has an easy API - beware version problems (2.7 vs 3.4)
Support timexes and events; start point for replication is Hector Llorens' NLDB paper: "Evaluating EmotiBlog Robustness for Sentiment Analysis Tasks" doi:10.1007/978-3-642-22327-3_41
In the README is fine - perhaps use the implementation from the Pheme/Kafka entity annotation code
extend with: - add training example - train - generic abstraction for classifier parameters - save model
now a json format is decided, add options for input and output format (input defaults to conll; output defaults to whatever input is)
To help reproducibility, and to track the critical information of clusters/embeddings and feature extractors used, it makes sense to store this metadata about models at the time the model is...
So that train_tagger and run_tagger use the same API