Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning

TL;DR

This paper introduces a novel joint training method for retrieval and programming models in complex knowledge base question answering, using weak supervision to improve performance and reduce manual labeling efforts.

Contribution

It presents the first joint training approach for retrieval and programmer models using weak supervision in knowledge base QA.

Findings

Achieved state-of-the-art results on a large-scale complex QA task.

Automatically learned retrieval model enhances question answering accuracy.

Reduced need for manual question labeling in training.

Abstract

A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training questions to the test question, meta-learning enables the programmer to adapt to unseen questions to tackle potential distributional biases quickly. However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive. In this paper, we present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision, i.e., the system's performance with respect to the produced answers. To the best of our knowledge, this is the first attempt to train the retrieval model with the programmer jointly. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases. We have released our code at https://github.com/DevinJake/MARL.