Detecting Interrogative Utterances with Recurrent Neural Networks
This work addresses a specific task in speech and language processing, but it is incremental as it compares existing methods and datasets without introducing major innovations.
The paper tackled the problem of classifying utterances as questions or statements using neural network architectures, achieving competitive performance on MSR-Skype and CALLHOME datasets.
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.