Coupling Distributed and Symbolic Execution for Natural Language Queries

Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor's intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.

• Publication year

  2016

• Venue

  International Conference on Machine Learning

• Publication date

  2016-12-08

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1612.02741
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Chunk-Based Bi-Scale Decoder for Neural Machine Translation

  2017cited by this paper
• A Network-based End-to-End Trainable Task-oriented Dialogue System

  2016cited by this paper
• Neural Enquirer: Learning to Query Tables in Natural Language

  2016cited by this paper
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

  2016influential reference
• Coverage Embedding Models for Neural Machine Translation

  2016cited by this paper
• Sequence-based Structured Prediction for Semantic Parsing

  2016cited by this paper
• Language to Logical Form with Neural Attention

  2016cited by this paper
• Inferring Logical Forms From Denotations

  2016cited by this paper
• Rationalizing Neural Predictions

  2016cited by this paper
• Simpler Context-Dependent Logical Forms via Model Projections

  2016cited by this paper
• Harnessing Deep Neural Networks with Logic Rules

  2016cited by this paper
• Compositional Semantic Parsing on Semi-Structured Tables

  2015cited by this paper
• Neural Programmer: Inducing Latent Programs with Gradient Descent

  2015cited by this paper
• Neural Programmer-Interpreters

  2015cited by this paper
• RECURRENT NEURAL NETWORKS

  2015influential reference
• Neural Generative Question Answering

  2015influential reference
• Reinforcement Learning Neural Turing Machines

  2015cited by this paper
• Neural Turing Machines

  2014cited by this paper
• Semantic Parsing on Freebase from Question-Answer Pairs

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding

  2013influential reference
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

  2004cited by this paper
• Reinforcement Learning: An Introduction

  1998cited by this paper
• Introduction to Reinforcement Learning

  1998cited by this paper
• Serial Order: A Parallel Distributed Processing Approach

  1997cited by this paper

• LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning

  2023cites this paper
• Weakly Supervised Reasoning by Neuro-Symbolic Approaches

  2023cites this paper
• The Emergence of Chunking Structures with Hierarchical HRNN

  2023cites this paper
• Towards Data-And Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing

  2022cites this paper
• Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing

  2022cites this paper
• Weakly Supervised Semantic Parsing by Learning from Mistakes

  2021cites this paper
• A hybrid E-learning recommendation integrating adaptive profiling and sentiment analysis

  2021cites this paper
• Neuro-symbolic artificial intelligence

  2021cites this paper
• A reasoning enhance network for muti-relation question answering

  2021cites this paper
• WabiQA: A Wikipedia-Based Thai Question-Answering System

  2021cites this paper
• Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

  2021cites this paper
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

  2021cites this paper
• Finding decision jumps in text classification

  2020cites this paper
• Conversational artificial intelligence - demystifying statistical vs linguistic NLP solutions

  2020cites this paper
• Improving Self-Attention Networks With Sequential Relations

  2020cites this paper
• Text Classification for Azerbaijani Language Using Machine Learning and Embedding

  2019cites this paper
• Querying NoSQL with Deep Learning to Answer Natural Language Questions

  2019cites this paper
• HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering

  2019cites this paper
• NADAQ: Natural Language Database Querying Based on Deep Learning

  2019cites this paper
• Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss

  2019cites this paper
• FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase

  2019cites this paper
• An Imitation Learning Approach to Unsupervised Parsing

  2019cites this paper
• Response-Based and Counterfactual Learning for Sequence-to-Sequence Tasks in NLP

  2019cites this paper
• Learning to Transform Vietnamese Natural Language Queries into SQL Commands

  2019cites this paper
• Discreteness in Neural Natural Language Processing

  2019cites this paper
• Learning Logical Representations from Natural Languages with Weak Supervision and Back-Translation

  2019influential citation
• DeepAssist: Deep Knowledge Grounding for Factual and Conversational Natural Language Interfaces

  2019cites this paper
• What It Takes to Achieve 100% Condition Accuracy on WikiSQL

  2018cites this paper
• Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback

  2018cites this paper
• Learning to Generate Structured Queries from Natural Language with Indirect Supervision

  2018cites this paper
• Rationalizing Translation Elongation by Reinforcement Learning

  2018cites this paper
• Jumper: Learning When to Make Classification Decision in Reading

  2018cites this paper
• Semantic Parsing with Syntax- and Table-Aware SQL Generation

  2018cites this paper
• An Interpretable Reasoning Network for Multi-Relation Question Answering

  2018cites this paper
• Neural Approaches to Conversational AI

  2018cites this paper
• Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing

  2018cites this paper
• Chunk-Based Bi-Scale Decoder for Neural Machine Translation

  2017cites this paper
• An Encoder-Decoder Framework Translating Natural Language to Database Queries

  2017cites this paper
• Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning

  2017cites this paper
• Object-oriented Neural Programming (OONP) for Document Understanding

  2017cites this paper
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

  2017cites this paper
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

  2017cites this paper
• Symbolic Priors for RNN-based Semantic Parsing

  2017cites this paper