InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.
.. InsNet documentation master file, created by
sphinx-quickstart on Sun Mar 21 22:16:57 2021.
You can adapt this file completely to your liking, but it should at least
contain the root toctree
directive.
InsNet <https://github.com/chncwang/insnet>
_ (documentation <https://insnet.readthedocs.io/en/latest>
_) is a powerful neural network library aiming at building instance-dependent computation graphs. It is designed to support padding-free dynamic batching, thus allow users to focus on building the model for a single instance. This design has at least four advantages as follows:
hierarchical Transformers <https://www.aclweb.org/anthology/P19-1500.pdf>
_.To summarize, we believe that Padding-free Dynamic Batching is the feature that NLPers will dive into but is surprisingly not supported by today's deep learning libraries.
Besides, InsNet has the following features:
Studies using InsNet are listed as follows, and we are looking forward to enriching this list:
Unseen Target Stance Detection with Adversarial Domain Generalization <https://arxiv.org/pdf/2010.05471.pdf>
_Cue-word Driven Neural Response Generation with a Shrinking Vocabulary <https://arxiv.org/pdf/2010.04927.pdf>
_InsNet uses Apache 2.0 license allowing you to use it in any project. But if you use InsNet for research, please cite this paper as follows and declare it as an early version of InsNet since the paper of InsNet is not completed yet::
@article{wang2019n3ldg, title={N3LDG: A Lightweight Neural Network Library for Natural Language Processing}, author={Wang, Qiansheng and Yu, Nan and Zhang, Meishan and Han, Zijia and Fu, Guohong}, journal={Beijing Da Xue Xue Bao}, volume={55}, number={1}, pages={113--119}, year={2019}, publisher={Acta Scientiarum Naturalium Universitatis Pekinenis} }
Due to incorrect Git operations, the very early history of InsNet is erased, but you can see it in another repo <https://github.com/chncwang/N3LDG>
_.
If you have any question about InsNet, feel free to post an issue or send me an email: [email protected]
See the documentation <https://insnet.readthedocs.io/en/latest>
_ for more details.