Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.

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

[2]  Tom M. Mitchell,et al.  Leveraging Knowledge Bases in LSTMs for Improving Machine Reading , 2017, ACL.

[3]  Chen Sun,et al.  VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Yue Zhang,et al.  A Graph-to-Sequence Model for AMR-to-Text Generation , 2018, ACL.

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

[6]  Todor Mihaylov,et al.  Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge , 2018, ACL.

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

[8]  Trevor Darrell,et al.  Language-Conditioned Graph Networks for Relational Reasoning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[9]  Ralph Grishman,et al.  Distant Supervision for Relation Extraction with an Incomplete Knowledge Base , 2013, NAACL.

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

[11]  Christopher Meek,et al.  Semantic Parsing for Single-Relation Question Answering , 2014, ACL.

[12]  Chuang Gan,et al.  The Neuro-Symbolic Concept Learner: Interpreting Scenes Words and Sentences from Natural Supervision , 2019, ICLR.

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

[14]  Bowen Zhou,et al.  Improved Neural Relation Detection for Knowledge Base Question Answering , 2017, ACL.

[15]  Ming-Wei Chang,et al.  The Value of Semantic Parse Labeling for Knowledge Base Question Answering , 2016, ACL.

[16]  Quoc V. Le,et al.  QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension , 2018, ICLR.

[17]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[18]  Richard Socher,et al.  DCN+: Mixed Objective and Deep Residual Coattention for Question Answering , 2017, ICLR.

[19]  Taher H. Haveliwala.  Topic-sensitive PageRank , 2002, IEEE Trans. Knowl. Data Eng..

[20]  Yansong Feng,et al.  Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks , 2018, ArXiv.