Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
This addresses the challenge of expensive manual labeling in meta-learning for knowledge base question answering, making it more scalable for real-world applications.
The paper tackles the problem of complex question answering over knowledge bases by introducing a method that jointly learns a retrieval model and a programmer from weak supervision, eliminating the need for manually labeled similar questions. The system achieves state-of-the-art performance on a large-scale task.
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.