Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question. This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. Our retriever model trains a recurrent neural network that learns to sequentially retrieve evidence paragraphs in the reasoning path by conditioning on the previously retrieved documents. Our reader model ranks the reasoning paths and extracts the answer span included in the best reasoning path. Experimental results show state-of-the-art results in three open-domain QA datasets, showcasing the effectiveness and robustness of our method. Notably, our method achieves significant improvement in HotpotQA, outperforming the previous best model by more than 14 points.

[1]  Paolo Ferragina,et al.  Fast and Accurate Annotation of Short Texts with Wikipedia Pages , 2010, IEEE Software.

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

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

[4]  Tim Salimans,et al.  Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , 2016, NIPS.

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

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

[7]  Hakan Inan,et al.  Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling , 2016, ICLR.

[8]  Lior Wolf,et al.  Using the Output Embedding to Improve Language Models , 2016, EACL.

[9]  Richard Socher,et al.  Dynamic Coattention Networks For Question Answering , 2016, ICLR.

[10]  Richard Socher,et al.  Efficient and Robust Question Answering from Minimal Context over Documents , 2018, ACL.

[11]  Jaewoo Kang,et al.  Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering , 2018, EMNLP.

[12]  Rajarshi Das,et al.  Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading , 2018, ArXiv.

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

[14]  Christopher Clark,et al.  Simple and Effective Multi-Paragraph Reading Comprehension , 2017, ACL.

[15]  Percy Liang,et al.  Know What You Don’t Know: Unanswerable Questions for SQuAD , 2018, ACL.

[16]  Wei Zhang,et al.  Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering , 2017, ICLR.

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

[18]  Myle Ott,et al.  Scaling Neural Machine Translation , 2018, WMT.

[19]  Stefan Feuerriegel,et al.  Adaptive Document Retrieval for Deep Question Answering , 2018, EMNLP.

[20]  Wei Zhang,et al.  R3: Reinforced Ranker-Reader for Open-Domain Question Answering , 2018, AAAI.

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

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

[23]  Ramesh Nallapati,et al.  Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering , 2019, EMNLP.

[24]  Ming-Wei Chang,et al.  Natural Questions: A Benchmark for Question Answering Research , 2019, TACL.

[25]  Rajarshi Das,et al.  Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering , 2019, EMNLP.

[26]  Jimmy J. Lin,et al.  End-to-End Open-Domain Question Answering with BERTserini , 2019, NAACL.

[27]  Danqi Chen,et al.  A Discrete Hard EM Approach for Weakly Supervised Question Answering , 2019, EMNLP.

[28]  Mohit Bansal,et al.  Revealing the Importance of Semantic Retrieval for Machine Reading at Scale , 2019, EMNLP.

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

[30]  William W. Cohen,et al.  PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text , 2019, EMNLP.

[31]  Kyunghyun Cho,et al.  Passage Re-ranking with BERT , 2019, ArXiv.

[32]  Sameer Singh,et al.  Compositional Questions Do Not Necessitate Multi-hop Reasoning , 2019, ACL.

[33]  Ming-Wei Chang,et al.  Latent Retrieval for Weakly Supervised Open Domain Question Answering , 2019, ACL.

[34]  Ali Farhadi,et al.  Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index , 2019, ACL.

[35]  Hannaneh Hajishirzi,et al.  Multi-hop Reading Comprehension through Question Decomposition and Rescoring , 2019, ACL.

[36]  Masaaki Nagata,et al.  Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction , 2019, ACL.

[37]  Zhen Huang,et al.  Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension , 2019, ACL.

[38]  Chang Zhou,et al.  Cognitive Graph for Multi-Hop Reading Comprehension at Scale , 2019, ACL.

[39]  Rajarshi Das,et al.  Do Multi-hop Readers Dream of Reasoning Chains? , 2019, EMNLP.

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

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