This repository contains a collection of neural network models that we used to demostrate the utility of our dataset. These networks were trained using Pytorch.
A more detailed description of the wet lab protocol corpus can be found in this paper:
An Annotated Corpus for Machine Reading of Instructions in Wet Lab Protocols
Chaitanya Kulkarni, Wei Xu, Alan Ritter, Raghu Machiraju
In Proceedings of 16th Annual Conference of the North American Chapter
of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT, 2018)
Additional information regarding the action, entities and relations can be found here.
Also check out a working demo for sequence tagging and relation extraction using the methods in this repository.
[TO BE POPULATED]
For Maximum Entropy Model used to label all the actions, entities and relations
A maximum entropy approach to named entity
recognition.
Marek Rei and Helen Yannakoudakis
In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-2016)
For LSTM + CRF Model used for labelling actions and entities
Neural Architectures for Named Entity Recognition Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer In Proceedings of 14th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT, 2016)
Licensed under the MIT License.