Neural Enquirer: Learning to Query Tables with Natural Language

Abstract

We proposed Neural Enquirer as a neural network architecture to execute a natural language (NL) query on a knowledge-base (KB) for answers. Basically, Neural Enquirer finds the distributed representation of a query and then executes it on knowledge-base tables to obtain the answer as one of the values in the tables. Unlike similar efforts in end-to-end training of semantic parsers, Neural Enquirer is fully "neuralized": it not only gives distributional representation of the query and the knowledge-base, but also realizes the execution of compositional queries as a series of differentiable operations, with intermediate results (consisting of annotations of the tables at different levels) saved on multiple layers of memory. Neural Enquirer can be trained with gradient descent, with which not only the parameters of the controlling components and semantic parsing component, but also the embeddings of the tables and query words can be learned from scratch. The training can be done in an end-to-end fashion, but it can take stronger guidance, e.g., the step-by-step supervision for complicated queries, and benefit from it. Neural Enquirer is one step towards building neural network systems which seek to understand language by executing it on real-world. Our experiments show that Neural Enquirer can learn to execute fairly complicated NL queries on tables with rich structures.

References in corpus (2)

• ADADELTA: An Adaptive Learning Rate Method
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

Cited by in corpus (17)

• An Interpretable Reasoning Network for Multi-Relation Question Answering
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Neural Generative Question Answering
• Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
• Emulating Human Conversations using Convolutional Neural Network-based IR
• Semantic Parsing with Syntax- and Table-Aware SQL Generation
• Inferring Logical Forms From Denotations
• TabMCQ: A Dataset of General Knowledge Tables and Multiple-choice Questions
• Text-to-SQL Generation for Question Answering on Electronic Medical Records
• Coupling Distributed and Symbolic Execution for Natural Language Queries
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• Text2Math: End-to-end Parsing Text into Math Expressions
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Content-Based Table Retrieval for Web Queries
• Neural Programming by Example