AllenNLP makes it easy to design and evaluate new deep learning models for nearly any NLP problem, along with the infrastructure to easily run them in the cloud or on your laptop. AllenNLP includes reference implementations of high quality models for both core NLP problems (e.g. semantic role labeling) and NLP applications (e.g. textual entailment). AllenNLP supports loading "plugins" dynamically. A plugin is just a Python package that provides custom registered classes or additional allennlp subcommands. There is ecosystem of open source plugins, some of which are maintained by the AllenNLP team here at AI2, and some of which are maintained by the broader community. AllenNLP will automatically find any official AI2-maintained plugins that you have installed, but for AllenNLP to find personal or third-party plugins you've installed, you also have to create either a local plugins file named .allennlp_plugins in the directory where you run the allennlp command.
Features
- A library with well-thought-out abstractions encapsulating the common data and model operations that are done in NLP research
- A commandline tool for training PyTorch models
- A collection of pre-trained models that you can use to make predictions
- A collection of readable reference implementations of common / recent NLP models
- An experiment framework for doing replicable science
- A way to demo your research, open source and community driven
Project Samples
