Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
This work addresses discourse parsing for natural language processing researchers, presenting an incremental improvement in method.
The paper tackled discourse relation sense classification by using LSTM-based distributed argument representations combined with surface features in a neural network, with Bayesian optimization for hyperparameter tuning, achieving results in the CoNLL-2016 evaluation.
This paper describes the Georgia Tech team's approach to the CoNLL-2016 supplementary evaluation on discourse relation sense classification. We use long short-term memories (LSTM) to induce distributed representations of each argument, and then combine these representations with surface features in a neural network. The architecture of the neural network is determined by Bayesian hyperparameter search.