Breadth First Reasoning Graph for Multi-hop Question Answering

Recently Graph Neural Network (GNN) has been used as a promising tool in multi-hop question answering task. However, the unnecessary updations and simple edge constructions prevent an accurate answer span extraction in a more direct and interpretable way. In this paper, we propose a novel model of Breadth First Reasoning Graph (BFR-Graph), which presents a new message passing way that better conforms to the reasoning process. In BFR-Graph, the reasoning message is required to start from the question node and pass to the next sentences node hop by hop until all the edges have been passed, which can effectively prevent each node from over-smoothing or being updated multiple times unnecessarily. To introduce more semantics, we also define the reasoning graph as a weighted graph with considering the number of co-occurrence entities and the distance between sentences. Then we present a more direct and interpretable way to aggregate scores from different levels of granularity based on the GNN. On HotpotQA leaderboard, the proposed BFR-Graph achieves state-of-the-art on answer span prediction.

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

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

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

[4]  Wei Xu,et al.  Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network , 2020, IJCAI.

[5]  Zhe Gan,et al.  Hierarchical Graph Network for Multi-hop Question Answering , 2020, EMNLP.

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

[7]  Mausam,et al.  A Simple Yet Strong Pipeline for HotpotQA , 2020, EMNLP.

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

[9]  Anders Søgaard,et al.  Jointly Learning to Label Sentences and Tokens , 2018, AAAI.

[10]  Jifan Chen,et al.  Multi-hop Question Answering via Reasoning Chains , 2019, ArXiv.

[11]  Arman Cohan,et al.  Longformer: The Long-Document Transformer , 2020, ArXiv.

[12]  Sebastian Riedel,et al.  Constructing Datasets for Multi-hop Reading Comprehension Across Documents , 2017, TACL.

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

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

[15]  Julien Perez,et al.  Latent Question Reformulation and Information Accumulation for Multi-Hop Machine Reading , 2019 .

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

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

[18]  Paul N. Bennett,et al.  Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention , 2020, ICLR.

[19]  Ting Liu,et al.  Is Graph Structure Necessary for Multi-hop Question Answering? , 2020, EMNLP.

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

[21]  Bowen Zhou,et al.  Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs , 2019, ACL.

[22]  Ming Tu,et al.  Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents , 2020, AAAI.

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

[24]  Mohit Bansal,et al.  Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning , 2019, EMNLP/IJCNLP.