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.

Highlights

  • Open domain Question Answering (QA) is the task of finding answers to questions posed in natural language

  • We show that GRAFT-Nets are competitive with the state-of-the-art methods developed for text-only QA, and state-of-the art methods developed for Knowledge Bases (KBs)-only QA (§ 5.4)1

  • In this paper we investigate QA using text combined with an incomplete KB, a task which has received limited attention in the past

Read more

Summary

Introduction

Open domain Question Answering (QA) is the task of finding answers to questions posed in natural language. This required a specialized pipeline consisting of multiple machinelearned and hand-crafted modules (Ferrucci et al, 2010). The paradigm has shifted towards training end-to-end deep neural network models for the task (Chen et al, 2017; Liang et al, 2017; Raison et al, 2018; Talmor and Berant, 2018; Iyyer et al, 2017). Answer questions using a single information source, usually either text from an encyclopedia, or a single knowledge base (KB). The suitability of an information source for QA depends on both its coverage and.

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.