Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

Abstract

Open Domain Question Answering (QA) is evolving from complex pipelined systems to end-to-end deep neural networks. Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone. In this paper we look at a more practical setting, namely QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations. We construct a suite of benchmark tasks for this problem, varying the difficulty of questions, the amount of training data, and KB completeness. We show that GRAFT-Net is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting. Source code is available at https://github.com/OceanskySun/GraftNet .

arXiv commentEMNLP 2018

References in corpus (17)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Large-scale Simple Question Answering with Memory Networks
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• Quasar: Datasets for Question Answering by Search and Reading
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• Modeling Relational Data with Graph Convolutional Networks
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion
• Question Answering from Unstructured Text by Retrieval and Comprehension
• Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading
• Ruminating Reader: Reasoning with Gated Multi-Hop Attention
• Object-oriented Neural Programming (OONP) for Document Understanding

Cited by in corpus (6)

• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Knowledge-Aided Open-Domain Question Answering
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Collaborative Policy Learning for Open Knowledge Graph Reasoning
• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• Memory networks for consumer protection:unfairness exposed