Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots

Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene. In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors' roles (e.g., speaker and addressee) and their utterances. Unfortunately, complex interactions among the interlocutors' roles make it challenging to precisely capture conversational contexts and interlocutors' information. Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC. Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors. Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee. Finally, we construct a corpus for RGMPC based on an existing open-access dataset. Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.

[1]  Wolfgang Minker,et al.  Are You Addressing Me? Multimodal Addressee Detection in Human-Human-Computer Conversations , 2017, SPECOM.

[2]  Paulo Rodrigo Cavalin,et al.  A Hybrid Architecture for Multi-Party Conversational Systems , 2017, ArXiv.

[3]  Verena Rieser,et al.  Why We Need New Evaluation Metrics for NLG , 2017, EMNLP.

[4]  Alexander M. Rush,et al.  Abstractive Sentence Summarization with Attentive Recurrent Neural Networks , 2016, NAACL.

[5]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[6]  Zhi Jin,et al.  Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection , 2017, CIKM.

[7]  Dongyan Zhao,et al.  How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models , 2017, ACL.

[8]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[9]  Maolin Tang A Hybrid , 2010 .

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

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

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

[13]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[14]  Rui Zhang,et al.  Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs , 2017, AAAI.

[15]  Wolfgang Minker,et al.  Speech and Text Analysis for Multimodal Addressee Detection in Human-Human-Computer Interaction , 2017, INTERSPEECH.

[16]  Rui Yan,et al.  Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation , 2016, COLING.

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

[18]  Xiaoyan Zhu,et al.  Commonsense Knowledge Aware Conversation Generation with Graph Attention , 2018, IJCAI.

[19]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[20]  Percy Liang,et al.  Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings , 2017, ACL.

[21]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[22]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[23]  Steve Renals,et al.  Recognition of Dialogue Acts in Multiparty Meetings Using a Switching DBN , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[24]  Jun Zhao,et al.  Curriculum Learning for Natural Answer Generation , 2018, IJCAI.

[25]  Jun Zhao,et al.  Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning , 2017, ACL.

[26]  Yuta Tsuboi,et al.  Addressee and Response Selection for Multi-Party Conversation , 2016, EMNLP.