Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph

Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation. Existing approaches that integrate commonsense knowledge into generative pre-trained language models simply transfer relational knowledge by post-training on individual knowledge triples while ignoring rich connections within the knowledge graph. We argue that exploiting both the structural and semantic information of the knowledge graph facilitates commonsense-aware text generation. In this paper, we propose Generation with Multi-Hop Reasoning Flow (GRF) that enables pre-trained models with dynamic multi-hop reasoning on multi-relational paths extracted from the external commonsense knowledge graph. We empirically show that our model outperforms existing baselines on three text generation tasks that require reasoning over commonsense knowledge. We also demonstrate the effectiveness of the dynamic multi-hop reasoning module with reasoning paths inferred by the model that provide rationale to the generation.

[1]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[2]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

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

[4]  Doug Downey,et al.  Abductive Commonsense Reasoning , 2019, ICLR.

[5]  Hung-yi Lee,et al.  DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs , 2019, EMNLP.

[6]  Yejin Choi,et al.  COMET: Commonsense Transformers for Automatic Knowledge Graph Construction , 2019, ACL.

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

[8]  Zhen-Hua Ling,et al.  Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models , 2019, ArXiv.

[9]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[10]  Yue Zhang,et al.  Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation , 2019, ACL.

[11]  Nicola De Cao,et al.  Question Answering by Reasoning Across Documents with Graph Convolutional Networks , 2018, NAACL.

[12]  Wenhu Chen,et al.  Variational Knowledge Graph Reasoning , 2018, NAACL.

[13]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

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

[15]  Catherine Havasi,et al.  Representing General Relational Knowledge in ConceptNet 5 , 2012, LREC.

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

[17]  Xiang Ren,et al.  KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning , 2019, EMNLP.

[18]  Lei Li,et al.  Enhancing Topic-to-Essay Generation with External Commonsense Knowledge , 2019, ACL.

[19]  Nathanael Chambers,et al.  A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories , 2016, NAACL.

[20]  Nan Duan,et al.  Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering , 2019, AAAI.

[21]  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.

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

[23]  Yejin Choi,et al.  ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning , 2019, AAAI.

[24]  Diego Marcheggiani,et al.  Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling , 2017, EMNLP.

[25]  Minlie Huang,et al.  Story Ending Generation with Incremental Encoding and Commonsense Knowledge , 2018, AAAI.

[26]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[27]  Quoc V. Le,et al.  A Simple Method for Commonsense Reasoning , 2018, ArXiv.

[28]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[29]  Seungwhan Moon,et al.  OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs , 2019, ACL.

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

[31]  Minlie Huang,et al.  A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation , 2020, TACL.

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

[33]  Lei Li,et al.  Dynamically Fused Graph Network for Multi-hop Reasoning , 2019, ACL.

[34]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[35]  Mohit Bansal,et al.  Commonsense for Generative Multi-Hop Question Answering Tasks , 2018, EMNLP.

[36]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[37]  Zheng-Yu Niu,et al.  Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs , 2019, EMNLP.

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

[39]  C. Lawrence Zitnick,et al.  CIDEr: Consensus-based image description evaluation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).