About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Haitian Sun
- sl:arxiv_num : 2102.07043
- sl:arxiv_published : 2021-02-14T01:29:54Z
- sl:arxiv_summary : We present the Open Predicate Query Language (OPQL); a method for
constructing a virtual KB (VKB) trained entirely from text. Large Knowledge
Bases (KBs) are indispensable for a wide-range of industry applications such as
question answering and recommendation. Typically, KBs encode world knowledge in
a structured, readily accessible form derived from laborious human annotation
efforts. Unfortunately, while they are extremely high precision, KBs are
inevitably highly incomplete and automated methods for enriching them are far
too inaccurate. Instead, OPQL constructs a VKB by encoding and indexing a set
of relation mentions in a way that naturally enables reasoning and can be
trained without any structured supervision. We demonstrate that OPQL
outperforms prior VKB methods on two different KB reasoning tasks and,
additionally, can be used as an external memory integrated into a language
model (OPQL-LM) leading to improvements on two open-domain question answering
tasks.@en
- sl:arxiv_title : Reasoning Over Virtual Knowledge Bases With Open Predicate Relations@en
- sl:arxiv_updated : 2021-06-14T19:34:42Z
- sl:bookmarkOf : https://arxiv.org/abs/2102.07043
- sl:creationDate : 2021-06-20
- sl:creationTime : 2021-06-20T08:30:31Z
- sl:relatedDoc :
Documents with similar tags (experimental)