Dialogue-act-driven Conversation Model : An Experimental Study

The utility of additional semantic information for the task of next utterance selection in an automated dialogue system is the focus of study in this paper. In particular, we show that additional information available in the form of dialogue acts –when used along with context given in the form of dialogue history– improves the performance irrespective of the underlying model being generative or discriminative. In order to show the model agnostic behavior of dialogue acts, we experiment with several well-known models such as sequence-to-sequence encoder-decoder model, hierarchical encoder-decoder model, and Siamese-based models with and without hierarchy; and show that in all models, incorporating dialogue acts improves the performance by a significant margin. We, furthermore, propose a novel way of encoding dialogue act information, and use it along with hierarchical encoder to build a model that can use the sequential dialogue act information in a natural way. Our proposed model achieves an MRR of about 84.8% for the task of next utterance selection on a newly introduced Daily Dialogue dataset, and outperform the baseline models. We also provide a detailed analysis of results including key insights that explain the improvement in MRR because of dialog act information.

[1]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[2]  Maxine Eskénazi,et al.  Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders , 2017, ACL.

[3]  Bowen Zhou,et al.  Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation , 2016, AAAI.

[4]  Harshit Kumar,et al.  Dialogue Act Sequence Labeling using Hierarchical encoder with CRF , 2017, AAAI.

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

[6]  Peter Young,et al.  Smart Reply: Automated Response Suggestion for Email , 2016, KDD.

[7]  Enrique Alfonseca,et al.  Learning to Attend, Copy, and Generate for Session-Based Query Suggestion , 2017, CIKM.

[8]  Joelle Pineau,et al.  A Survey of Available Corpora for Building Data-Driven Dialogue Systems , 2015, Dialogue Discourse.

[9]  Joelle Pineau,et al.  The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems , 2015, SIGDIAL Conference.

[10]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[11]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[12]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[13]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

[14]  Andreas Stolcke,et al.  The ICSI Meeting Corpus , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[15]  Joelle Pineau,et al.  Generative Deep Neural Networks for Dialogue: A Short Review , 2016, ArXiv.

[16]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

[17]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

[18]  Ricardo Ribeiro,et al.  The Influence of Context on Dialogue Act Recognition , 2015, ArXiv.

[19]  Jörg Tiedemann,et al.  News from OPUS — A collection of multilingual parallel corpora with tools and interfaces , 2009 .

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

[21]  Joelle Pineau,et al.  Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus , 2017, Dialogue Discourse.

[22]  Xiaoyu Shen,et al.  DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset , 2017, IJCNLP.