Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

Abstract

This paper addresses the problem of mapping natural language sentences to lambda-calculus encodings of their meaning. We describe a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus. The algorithm induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. We apply the method to the task of learning natural language interfaces to databases and show that the learned parsers outperform previous methods in two benchmark database domains.

Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)

References in corpus (1)

• Acquiring Word-Meaning Mappings for Natural Language Interfaces

Cited by in corpus (167)

• Kernel methods in machine learning
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• A Convolutional Neural Network for Modelling Sentences
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• TabFact: A Large-scale Dataset for Table-based Fact Verification
• Improving Text-to-SQL Evaluation Methodology
• Grounded Language Learning in a Simulated 3D World
• MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
• Language to Logical Form with Neural Attention
• A Syntactic Neural Model for General-Purpose Code Generation
• DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
• Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language
• Learning Dependency-Based Compositional Semantics
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
• IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
• One Model for the Learning of Language
• Neural Module Networks for Reasoning over Text
• Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• Grammar-based Neural Text-to-SQL Generation
• Learning to Compose Words into Sentences with Reinforcement Learning
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• Coarse-to-Fine Decoding for Neural Semantic Parsing
• Modifying Memories in Transformer Models
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
• Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
• Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
• Abstract Syntax Networks for Code Generation and Semantic Parsing
• FVQA: Fact-based Visual Question Answering
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases
• Neural Enquirer: Learning to Query Tables with Natural Language
• Data Recombination for Neural Semantic Parsing
• Measuring Compositionality in Representation Learning
• Improving Text-to-SQL with Schema Dependency Learning
• Generalized Grounding Graphs: A Probabilistic Framework for Understanding Grounded Commands
• A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text
• SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
• Simpler Context-Dependent Logical Forms via Model Projections
• A Survey on Semantic Parsing
• Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation
• Sketching Robot Programs On the Fly
• Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
• TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
• TreeGen: A Tree-Based Transformer Architecture for Code Generation
• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
• Refining Language Models with Compositional Explanations
• A Discrete Hard EM Approach for Weakly Supervised Question Answering
• Show Your Work: Scratchpads for Intermediate Computation with Language Models
• Adversarial TableQA: Attention Supervision for Question Answering on Tables
• Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
• Learning Structured Natural Language Representations for Semantic Parsing
• Spatial Dependency Parsing for Semi-Structured Document Information Extraction
• Question Answering over Knowledge Base using Language Model Embeddings
• Structured Reordering for Modeling Latent Alignments in Sequence Transduction
• Semantic Parsing with Syntax- and Table-Aware SQL Generation
• Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention
• Alignment-based compositional semantics for instruction following
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Multi-hop Reading Comprehension through Question Decomposition and Rescoring
• Inferring Logical Forms From Denotations
• Cornell SPF: Cornell Semantic Parsing Framework
• Transfer Learning for Neural Semantic Parsing
• Neural Proof Nets
• Using Inverse lambda and Generalization to Translate English to Formal Languages
• Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
• Building a Neural Semantic Parser from a Domain Ontology
• VQA-LOL: Visual Question Answering under the Lens of Logic
• Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction
• Why Build an Assistant in Minecraft?
• Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
• Photon: A Robust Cross-Domain Text-to-SQL System
• Something Old, Something New: Grammar-based CCG Parsing with Transformer Models
• Toward Code Generation: A Survey and Lessons from Semantic Parsing
• Bidirectional Attention for SQL Generation
• Solving puzzles described in English by automated translation to answer set programming and learning how to do that translation
• Question Answering over Knowledge Graphs via Structural Query Patterns
• Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems
• Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization
• Semantic Understanding of Professional Soccer Commentaries
• Syntactic Scaffolds for Semantic Structures
• Generating Logical Forms from Graph Representations of Text and Entities
• Parser for Abstract Meaning Representation using Learning to Search
• Compositional Generalization via Semantic Tagging
• JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation
• Grounded Adaptation for Zero-shot Executable Semantic Parsing
• Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• Break It Down: A Question Understanding Benchmark
• Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning
• VASTA: A Vision and Language-assisted Smartphone Task Automation System
• Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs
• Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
• UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
• Learning a natural-language to LTL executable semantic parser for grounded robotics
• Unsupervised Learning of KB Queries in Task-Oriented Dialogs
• SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases
• Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations
• An Imitation Game for Learning Semantic Parsers from User Interaction
• Towards Property-Based Tests in Natural Language
• Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models
• Building an Application Independent Natural Language Interface
• Left-corner Methods for Syntactic Modeling with Universal Structural Constraints
• Multi-Instance Learning for End-to-End Knowledge Base Question Answering
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• Zero-shot Transfer Learning for Semantic Parsing
• Question Generation from SQL Queries Improves Neural Semantic Parsing
• Knowledge Graph Question Answering via SPARQL Silhouette Generation
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job
• Program Synthesis using Natural Language
• Teaching Machine Comprehension with Compositional Explanations
• Semantic Parsing with Dual Learning
• Dependency-based Hybrid Trees for Semantic Parsing
• Cross-lingual Semantic Parsing
• Grounded Discovery of Coordinate Term Relationships between Software Entities
• Learning an Executable Neural Semantic Parser
• Improving Semantic Parsing with Neural Generator-Reranker Architecture
• A Survey on Semantic Parsing from the perspective of Compositionality
• Learning Adaptive Language Interfaces through Decomposition
• Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models
• Self-supervised Text-to-SQL Learning with Header Alignment Training
• mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer
• Learning to Synthesize Data for Semantic Parsing
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network
• Optimal Neural Program Synthesis from Multimodal Specifications
• Multi-modal Synthesis of Regular Expressions
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• Merging Weak and Active Supervision for Semantic Parsing
• Sentence Rewriting for Semantic Parsing
• Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
• Neural Compositional Denotational Semantics for Question Answering
• Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following
• Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings
• Learning Executable Semantic Parsers for Natural Language Understanding
• Contextual Media Retrieval Using Natural Language Queries
• Simple, Fast Semantic Parsing with a Tensor Kernel
• Discourse in Multimedia: A Case Study in Information Extraction
• Unsupervised Grammar Induction with Depth-bounded PCFG
• Reasoning-Driven Question-Answering for Natural Language Understanding
• A survey of cross-lingual features for zero-shot cross-lingual semantic parsing
• Look-up and Adapt: A One-shot Semantic Parser
• A Sketch-Based System for Semantic Parsing
• A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
• Language understanding as a step towards human level intelligence - automatizing the construction of the initial dictionary from example sentences
• LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing
• Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing
• Calculating Question Similarity is Enough: A New Method for KBQA Tasks
• A Generative Model for Joint Natural Language Understanding and Generation
• SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts
• multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning
• A Globally Normalized Neural Model for Semantic Parsing
• Grounded Graph Decoding Improves Compositional Generalization in Question Answering
• Context Dependent Semantic Parsing: A Survey
• From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
• Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations
• Multilingual Neural Semantic Parsing for Low-Resourced Languages
• Probabilistic Graph Reasoning for Natural Proof Generation
• Enforcing Consistency in Weakly Supervised Semantic Parsing
• Learning Algebraic Recombination for Compositional Generalization
• Semantic Parsing: Syntactic assurance to target sentence using LSTM Encoder CFG-Decoder
• Sequence to Logic with Copy and Cache
• Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds
• Learning to Learn Semantic Parsers from Natural Language Supervision
• Learning to Generate Structured Queries from Natural Language with Indirect Supervision