Keyword-Guided Neural Conversational Model

We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e.g., recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for next-turn keyword classification are directly extracted from conversations without human annotations, thus, they are noisy and have low correlation with human judgements, and 2) during keyword transition, the agents solely rely on the similarities between word embeddings to move closer to the target keyword, which may not reflect how humans converse. In this paper, we assume that human conversations are grounded on commonsense and propose a keyword-guided neural conversational model that can leverage external commonsense knowledge graphs (CKG) for both keyword transition and response retrieval. Automatic evaluations suggest that commonsense improves the performance of both next-turn keyword prediction and keyword-augmented response retrieval. In addition, both self-play and human evaluations show that our model produces responses with smoother keyword transition and reaches the target keyword faster than competitive baselines.

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

[2]  Chunyan Miao,et al.  CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts , 2020, AAAI.

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

[4]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[5]  Xiyuan Zhang,et al.  Proactive Human-Machine Conversation with Explicit Conversation Goal , 2019, ACL.

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

[7]  Henry Lieberman,et al.  Beating Common Sense into Interactive Applications , 2004, AI Mag..

[8]  Xiaodan Liang,et al.  Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation , 2020, AAAI.

[9]  Zhe Gan,et al.  Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization , 2018, NeurIPS.

[10]  Emanuel A. Schegloff,et al.  Conversation analysis and socially shared cognition , 1991, Perspectives on socially shared cognition.

[11]  Zheng-Yu Niu,et al.  Knowledge Graph Grounded Goal Planning for Open-Domain Conversation Generation , 2020, AAAI.

[12]  Hao Wang,et al.  Towards Persona-Based Empathetic Conversational Models , 2020, EMNLP.

[13]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[14]  Joelle Pineau,et al.  The Second Conversational Intelligence Challenge (ConvAI2) , 2019, The NeurIPS '18 Competition.

[15]  Erik Cambria,et al.  Augmenting End-to-End Dialogue Systems With Commonsense Knowledge , 2018, AAAI.

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

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

[18]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[19]  Eric P. Xing,et al.  Target-Guided Open-Domain Conversation , 2019, ACL.

[20]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[23]  Y-Lan Boureau,et al.  Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset , 2018, ACL.

[24]  Zheng-Yu Niu,et al.  Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation , 2020, ACL.

[25]  Daniel Jurafsky,et al.  A Simple, Fast Diverse Decoding Algorithm for Neural Generation , 2016, ArXiv.

[26]  Jason Weston,et al.  Wizard of Wikipedia: Knowledge-Powered Conversational agents , 2018, ICLR.

[27]  Chunyan Miao,et al.  An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss , 2018, AAAI.

[28]  Kenneth Mark Colby,et al.  Artificial Paranoia , 1975, Artif. Intell..

[29]  Lihong Li,et al.  Neural Approaches to Conversational AI , 2019, Found. Trends Inf. Retr..

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

[31]  Henry Lieberman,et al.  A commonsense approach to predictive text entry , 2004, CHI EA '04.