Case-based Reasoning for Natural Language Queries over Knowledge Bases

Abstract

It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions -- a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach (CBR-KBQA) for question answering over large knowledge bases. CBR-KBQA consists of a nonparametric memory that stores cases (question and logical forms) and a parametric model that can generate a logical form for a new question by retrieving cases that are relevant to it. On several KBQA datasets that contain complex questions, CBR-KBQA achieves competitive performance. For example, on the ComplexWebQuestions dataset, CBR-KBQA outperforms the current state of the art by 11\% on accuracy. Furthermore, we show that CBR-KBQA is capable of using new cases \emph{without} any further training: by incorporating a few human-labeled examples in the case memory, CBR-KBQA is able to successfully generate logical forms containing unseen KB entities as well as relations.

arXiv commentEMNLP 2021

References in corpus (11)

• Overcoming catastrophic forgetting in neural networks
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Large-scale Simple Question Answering with Memory Networks
• MBT: A Memory-Based Part of Speech Tagger-Generator
• DeepCoder: Learning to Write Programs
• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Generative Language Modeling for Automated Theorem Proving
• A Simple Approach to Case-Based Reasoning in Knowledge Bases