Neural enquirer: learning to query tables in natural language

Abstract

We propose NEURAL ENQUIRER — a neural network architecture for answering natural language (NL) questions based on a knowledge base (KB) table. Unlike existing work on end-to-end training of semantic parsers [Pasupat and Liang, 2015; Neelakantan et al., 2015], NEURAL ENQUIRER is fully “neuralized”: it finds distributed representations of queries and KB tables, and executes queries through a series of neural network components called “executors”. Executors model query operations and compute intermediate execution results in the form of table annotations at different levels. NEURAL ENQUIRER can be trained with gradient descent, with which the representations of queries and the KB table are jointly optimized with the query execution logic. The training can be done in an end-to-end fashion, and it can also be carried out with stronger guidance, e.g., step-by-step supervision for complex queries. NEURAL ENQUIRER is one step towards building neural network systems that can understand natural language in real-world tasks. As a proof-of-concept, we conduct experiments on a synthetic QA task, and demonstrate that the model can learn to execute reasonably complex NL queries on small-scale KB tables.