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.
@article{arxiv.1606.04503,
title = {Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization},
author = {Akanksha and Jacob Eisenstein},
journal= {arXiv preprint arXiv:1606.04503},
year = {2016}
}
Comments
describes our system at the CoNLL 2016 shared task