VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering

TL;DR

VisKoP is an interactive platform that converts natural language questions into knowledge programs, allowing users to visually edit and debug queries to improve question answering over large knowledge bases.

Contribution

The paper introduces VisKoP, a novel system combining neural program induction, graphical editing, and efficient execution for knowledge base question answering.

Findings

High efficiency in handling large-scale knowledge bases

User interaction significantly improves query correctness

System achieves effective question answering with interactive debugging

Abstract

We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program induction module, which converts natural language questions into knowledge oriented program language (KoPL), but also maps KoPL programs into graphical elements. KoPL programs can be edited with simple graphical operators, such as dragging to add knowledge operators and slot filling to designate operator arguments. Moreover, VisKoP provides auto-completion for its knowledge base schema and users can easily debug the KoPL program by checking its intermediate results. To facilitate the practical KBQA on a million-entity-level KB, we design a highly efficient KoPL execution engine for the back-end. Experiment results show that VisKoP is highly efficient and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. The VisKoP online demo https://demoviskop.xlore.cn (Stable release of this paper) and https://viskop.xlore.cn (Beta release with new features), highly efficient KoPL engine https://pypi.org/project/kopl-engine, and screencast video https://youtu.be/zAbJtxFPTXo are now publicly available.