Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research academia and industry. In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance. More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources. Afterward, we use a pre-trained language model to encode the question, retrieved knowledge and choices, and propose an answer choice-aware attention mechanism to fuse all hidden representations of the previous modules. Finally, the linear classifier for specific tasks is used to predict the answer. Experimental results on the CommonsenseQA dataset show that our method significantly outperforms other competitive methods and achieves the new state-of-the-art. In addition, further ablation studies demonstrate the effectiveness of our graph-based iterative knowledge retrieval module and the answer choice-aware attention module in retrieving and synthesizing background knowledge from multiple knowledge sources.

[1]  Richard Socher,et al.  Explain Yourself! Leveraging Language Models for Commonsense Reasoning , 2019, ACL.

[2]  Danqi Chen,et al.  CoQA: A Conversational Question Answering Challenge , 2018, TACL.

[3]  Daniel Khashabi,et al.  UnifiedQA: Crossing Format Boundaries With a Single QA System , 2020, EMNLP.

[4]  Oren Etzioni,et al.  Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge , 2018, ArXiv.

[5]  Jonathan Berant,et al.  CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge , 2019, NAACL.

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

[7]  Yiming Yang,et al.  XLNet: Generalized Autoregressive Pretraining for Language Understanding , 2019, NeurIPS.

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

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

[10]  Nanyun Peng,et al.  Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering , 2020, EMNLP.

[11]  Yu Cheng,et al.  FreeLB: Enhanced Adversarial Training for Natural Language Understanding , 2020, ICLR.

[12]  Zijian Wang,et al.  Answering Complex Open-domain Questions Through Iterative Query Generation , 2019, EMNLP.

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

[14]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[15]  Pascale Fung,et al.  Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems , 2018, ACL.

[16]  Hua Wu,et al.  An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge , 2017, ACL.

[17]  Yoshua Bengio,et al.  HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering , 2018, EMNLP.

[18]  Zhiyuan Liu,et al.  Denoising Distantly Supervised Open-Domain Question Answering , 2018, ACL.

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

[20]  Rajarshi Das,et al.  Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering , 2019, ICLR.

[21]  Yejin Choi,et al.  Social IQA: Commonsense Reasoning about Social Interactions , 2019, EMNLP 2019.

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

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

[24]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[25]  Colin Raffel,et al.  Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer , 2019, J. Mach. Learn. Res..

[26]  Kevin Gimpel,et al.  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations , 2019, ICLR.

[27]  Richard Socher,et al.  Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering , 2019, ICLR.

[28]  Ran El-Yaniv,et al.  Multi-Hop Paragraph Retrieval for Open-Domain Question Answering , 2019, ACL.

[29]  Eunsol Choi,et al.  TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension , 2017, ACL.

[30]  Nan Duan,et al.  Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base , 2019, EMNLP.

[31]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[32]  Danqi Chen,et al.  Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering , 2019, ArXiv.

[33]  Chitta Baral,et al.  Careful Selection of Knowledge to Solve Open Book Question Answering , 2019, ACL.

[34]  Ying Zhang,et al.  Task-Oriented Conversation Generation Using Heterogeneous Memory Networks , 2019, EMNLP.

[35]  Yi Yang,et al.  WikiQA: A Challenge Dataset for Open-Domain Question Answering , 2015, EMNLP.

[36]  Eneko Agirre,et al.  SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation , 2017, *SEMEVAL.

[37]  Peter Clark,et al.  Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering , 2018, EMNLP.

[38]  Hai Zhao,et al.  Retrospective Reader for Machine Reading Comprehension , 2020, ArXiv.

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

[40]  Jason Weston,et al.  Reading Wikipedia to Answer Open-Domain Questions , 2017, ACL.