Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
This addresses the issue of incomplete knowledge bases for applications like question answering and recommendation, offering an incremental improvement over existing virtual KB methods.
The authors tackled the problem of incomplete knowledge bases by introducing OPQL, a method for constructing virtual knowledge bases from text without structured supervision, which outperformed prior methods on reasoning tasks and improved question answering when integrated with language models.
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.