papers AI Learner
The Github is limit! Click to go to the new site.

Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization

2016-06-14
Akanksha, Jacob Eisenstein

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1606.04503

PDF

https://arxiv.org/pdf/1606.04503


Similar Posts

Comments