Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization

Abstract

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.

describes our system at the CoNLL 2016 shared task