Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs

Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous work. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models.

[1]  Mitesh M. Khapra,et al.  Towards Exploiting Background Knowledge for Building Conversation Systems , 2018, EMNLP.

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

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

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

[5]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[6]  Ali Farhadi,et al.  Bidirectional Attention Flow for Machine Comprehension , 2016, ICLR.

[7]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[8]  Chin-Yew Lin,et al.  Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics , 2004, ACL.

[9]  Wenhan Xiong,et al.  DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning , 2017, EMNLP.

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

[11]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[12]  Zhen Xu,et al.  Incorporating Loose-Structured Knowledge into LSTM with Recall Gate for Conversation Modeling , 2016, ArXiv.

[13]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[14]  Alan Ritter,et al.  Data-Driven Response Generation in Social Media , 2011, EMNLP.

[15]  Rajarshi Das,et al.  Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks , 2017, ACL.

[16]  Xianchao Wu,et al.  Dialog Generation Using Multi-Turn Reasoning Neural Networks , 2018, NAACL.

[17]  Ruslan Salakhutdinov,et al.  Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text , 2018, EMNLP.

[18]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[19]  Hyunki Kim,et al.  Open domain question answering using Wikipedia-based knowledge model , 2014, Inf. Process. Manag..

[20]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[21]  Richard Socher,et al.  Multi-Hop Knowledge Graph Reasoning with Reward Shaping , 2018, EMNLP.

[22]  Tom M. Mitchell,et al.  Random Walk Inference and Learning in A Large Scale Knowledge Base , 2011, EMNLP.

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

[24]  Sangdo Han,et al.  Exploiting knowledge base to generate responses for natural language dialog listening agents , 2015, SIGDIAL Conference.

[25]  Yang Feng,et al.  Knowledge Diffusion for Neural Dialogue Generation , 2018, ACL.

[26]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[27]  Alexander J. Smola,et al.  Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning , 2017, ICLR.

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

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

[30]  Yu Zhang,et al.  Flexible End-to-End Dialogue System for Knowledge Grounded Conversation , 2017, ArXiv.

[31]  Ming-Wei Chang,et al.  A Knowledge-Grounded Neural Conversation Model , 2017, AAAI.

[32]  Rajarshi Das,et al.  Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks , 2016, EACL.

[33]  Jayant Krishnamurthy,et al.  Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge , 2017, AAAI.

[34]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.