Graph-based and transition-based neural dependency parsers
IMS Neural Dependency Parser is an extended re-implementation of the transition- and graph-based parsers described in Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
The parser was developed for the paper:
Agnieszka Falenska, Jonas Kuhn. The (Non-) Utility of Structural Features in BiLSTM-based Dependency Parsers. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
Later it was extended with multi-task training and deep contextualized embeddings for the paper:
Agnieszka Falenska, Anders Björkelund, and Jonas Kuhn. Integrating Graph-Based and Transition-Based Dependency Parsers in the Deep Contextualized Era. Proceedings of the 16th International Conference on Parsing Technologies.
See IMSnPars for the code and description of the parameters.