Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks

In this work, we present a model that incorporates Dialogue Act (DA) semantics in the framework of Recurrent Neural Networks (RNNs) for DA classification. Specifically, we propose a novel scheme for automatically encoding DA semantics via the extraction of salient keywords that are representative of the DA tags. The proposed model is applied to the Switchboard corpus and achieves 1.7% (absolute) improvement in classification accuracy with respect to the baseline model. We demonstrate that the addition of discourse-level features enhances the DA classification as well as makes the algorithm more robust: the proposed model does not require the preprocessing of dialogue transcriptions.

[1]  Gholamreza Haffari,et al.  A Latent Variable Recurrent Neural Network for Discourse Relation Language Models , 2016, ArXiv.

[2]  JurafskyDaniel,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000 .

[3]  Allen L. Gorin,et al.  Processing of semantic information in fluently spoken language , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[5]  M. Ostendorf,et al.  Using out-of-domain data to improve in-domain language models , 1997, IEEE Signal Processing Letters.

[6]  Elizabeth Shriberg,et al.  Switchboard SWBD-DAMSL shallow-discourse-function annotation coders manual , 1997 .

[7]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[8]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[9]  Franck Dernoncourt,et al.  Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks , 2016, NAACL.

[10]  Mark J. F. Gales,et al.  Discriminative map for acoustic model adaptation , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[11]  James F. Allen,et al.  Draft of DAMSL Dialog Act Markup in Several Layers , 2007 .

[12]  Phil Blunsom,et al.  Recurrent Convolutional Neural Networks for Discourse Compositionality , 2013, CVSM@ACL.

[13]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[14]  Rosalind W. Picard,et al.  Dialog Act Classification from Prosodic Features Using Support Vector Machines , 2002 .

[15]  A. Stolcke,et al.  Automatic detection of discourse structure for speech recognition and understanding , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[16]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[17]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[18]  Kôiti Hasida,et al.  ISO 24617-2: A semantically-based standard for dialogue annotation , 2012, LREC.

[19]  John R. Searle,et al.  Speech Acts: An Essay in the Philosophy of Language , 1970 .

[20]  Shrikanth S. Narayanan,et al.  Distributional Semantic Models for Affective Text Analysis , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[21]  Alessandro Moschitti,et al.  Semi-supervised Question Retrieval with Gated Convolutions , 2015, NAACL.

[22]  Ellen Riloff,et al.  Classifying Sentences as Speech Acts in Message Board Posts , 2011, EMNLP.

[23]  Navdeep Jaitly,et al.  Hybrid speech recognition with Deep Bidirectional LSTM , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[24]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[25]  Rodney D. Nielsen,et al.  Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network , 2016, COLING.

[26]  Antoine Raux,et al.  Dialog State Tracking Challenge Handbook , 2012 .

[27]  Regina Barzilay,et al.  Molding CNNs for text: non-linear, non-consecutive convolutions , 2015, EMNLP.

[28]  Carlo Strapparava,et al.  The Role of Affect Analysis in Dialogue Act Identification , 2013, IEEE Transactions on Affective Computing.

[29]  Elizabeth Shriberg,et al.  Automatic dialog act segmentation and classification in multiparty meetings , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[30]  Harry Bunt,et al.  Dialogue Act Annotation with the ISO 24617-2 Standard , 2017 .

[31]  Timothy Baldwin,et al.  Classifying Dialogue Acts in One-on-One Live Chats , 2010, EMNLP.

[32]  Kôiti Hasida,et al.  Towards an ISO Standard for Dialogue Act Annotation , 2010, LREC.