Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization

Add code
Jun 14, 2016
Akanksha, Jacob Eisenstein
Figure 1 for Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
Figure 2 for Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
Figure 3 for Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization
Figure 4 for Shallow Discourse Parsing Using Distributed Argument Representations and Bayesian Optimization

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon