About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Bhuwan Dhingra
- sl:arxiv_num : 2002.10640
- sl:arxiv_published : 2020-02-25T03:13:32Z
- sl:arxiv_summary : We consider the task of answering complex multi-hop questions using a corpus
as a virtual knowledge base (KB). In particular, we describe a neural module,
DrKIT, that traverses textual data like a KB, softly following paths of
relations between mentions of entities in the corpus. At each step the module
uses a combination of sparse-matrix TFIDF indices and a maximum inner product
search (MIPS) on a special index of contextual representations of the mentions.
This module is differentiable, so the full system can be trained end-to-end
using gradient based methods, starting from natural language inputs. We also
describe a pretraining scheme for the contextual representation encoder by
generating hard negative examples using existing knowledge bases. We show that
DrKIT improves accuracy by 9 points on 3-hop questions in the MetaQA dataset,
cutting the gap between text-based and KB-based state-of-the-art by 70%. On
HotpotQA, DrKIT leads to a 10% improvement over a BERT-based re-ranking
approach to retrieving the relevant passages required to answer a question.
DrKIT is also very efficient, processing 10-100x more queries per second than
existing multi-hop systems.@en
- sl:arxiv_title : Differentiable Reasoning over a Virtual Knowledge Base@en
- sl:arxiv_updated : 2020-02-25T03:13:32Z
- sl:bookmarkOf : https://arxiv.org/abs/2002.10640
- sl:creationDate : 2020-07-11
- sl:creationTime : 2020-07-11T14:03:19Z
- sl:relatedDoc : http://www.semanlink.net/doc/2020/07/end_to_end_learning_with_text_
Documents with similar tags (experimental)