Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks

Recent approaches for dialogue act recognition have shown that context from preceding utterances is important to classify the subsequent one. It was shown that the performance improves rapidly when the context is taken into account. We propose an utterance-level attention-based bidirectional recurrent neural network (Utt-Att-BiRNN) model to analyze the importance of preceding utterances to classify the current one. In our setup, the BiRNN is given the input set of current and preceding ut- terances. Our model outperforms previous models that use only preceding utterances as context on the used corpus. Another contribution of our research is a mechanism to discover the amount of information in each utterance to classify the subse- quent one and to show that context-based learning not only im- proves the performance but also achieves higher confidence in the recognition of dialogue acts. We use character- and word- level features to represent the utterances. The results are pre- sented for character and word feature representations and as an ensemble model of both representations. We found that when classifying short utterances, the closest preceding utterances contribute to a higher degree.

@InProceedings{BMWW18, 
 	 author =  {Bothe, Chandrakant and Magg, Sven and Weber, Cornelius and Wermter, Stefan},  
 	 title = {Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks}, 
 	 booktitle = {INTERSPEECH 2018},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {996--1000},
 	 year = {2018},
 	 month = {Sep},
 	 publisher = {ISCA},
 	 doi = {10.21437/Interspeech.2018-2527}, 
 }