English

Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization

Computation and Language 2016-06-15 v1

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.

Keywords

Cite

@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

R2 v1 2026-06-22T14:25:20.120Z