In this paper, we explore different neural network architectures that can predict if a speaker of a given utterance is asking a question or making a statement. We com- pare the outcomes of regularization methods that are popularly used to train deep neural networks and study how different context functions can affect the classification performance. We also compare the efficacy of gated activation functions that are favorably used in recurrent neural networks and study how to combine multimodal inputs. We evaluate our models on two multimodal datasets: MSR-Skype and CALLHOME.
@article{arxiv.1511.01042,
title = {Detecting Interrogative Utterances with Recurrent Neural Networks},
author = {Junyoung Chung and Jacob Devlin and Hany Hassan Awadalla},
journal= {arXiv preprint arXiv:1511.01042},
year = {2015}
}
Comments
6 pages, accepted to NIPS 2015 Workshop on Machine Learning for Spoken Language Understanding and Interaction