Neural Enquirer: Learning to Query Tables

By Pengcheng Yin, Zhengdong Lu, Hang Li, B. Kao. 2015

41 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Network-based End-to-End Trainable Task-oriented Dialogue System (2016, background): “They allow the creation of effective chatbot type systems but they lack any capability for supporting domain specific tasks, for example, being able to interact with databases (Sukhbaatar et al., 2015; Yin et al., 2015) and aggregate useful information into their responses.”
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA (2019, background): “Earlier attempts in multi-hop QA focused on reasoning about the relations in a knowledge base (Jain, 2016; Zhou et al., 2018; Lin et al., 2018) or tables (Yin et al., 2015).”
Learning Knowledge Base Inference with Neural Theorem Provers (2016, background): “Yin et al. (2015) and Andreas et al. (2016) map queries to multiple differentiable modules that can be used to retrieve answers from a KB. Clark et al. (2014) extract common-sense knowledge from textbooks in form of rules to improve KB inference by soft-matching and non-recursive forward inference.”
Conditional Generation and Snapshot Learning in Neural Dialogue Systems (2016, background): “However, these models are still far from real world applications because they lack any capability for supporting domain speciﬁc tasks, for example, being able to interact with databases (Sukhbaatar et al., 2015; Yin et al., 2016) and aggregate useful information into their responses.”
Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access (2016, methodology): “Our work is motivated by the neural GenQA (Yin et al., 2016a) and neural enquirer (Yin et al., 2016b) models for querying KBs via natural language in a fully “neuralized” way.”
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension (2019, unknown): “Earlier attempts in multi-hop MRC focused on reasoning about the relations in a knowledge base (Jain, 2016; Zhou et al., 2018; Lin et al., 2018) or tables (Yin et al., 2015).”
End-to-End Reinforcement Learning of Dialogue Agents for Information Access (2016, background): “Groundhog Day is a Bill Murray movie which came out in 1993.”
Neural Generative Question Answering (2015, background): “On the other hand, the recent success of memory-based neural network models has greatly extended the ways of storing and accessing text information, in both short-term memory (e.g., in [Bahdanau et al., 2015]) and long-term memory (e.g., in [Weston et al., 2015]).”