Lambda Dependency-Based Compositional Semantics
arXiv:1309.4408
Abstract
This short note presents a new formal language, lambda dependency-based compositional semantics (lambda DCS) for representing logical forms in semantic parsing. By eliminating variables and making existential quantification implicit, lambda DCS logical forms are generally more compact than those in lambda calculus.
Cited by in corpus (27)
- Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
- IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
- Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
- Simpler Context-Dependent Logical Forms via Model Projections
- A Survey on Semantic Parsing
- Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
- Learning Structured Natural Language Representations for Semantic Parsing
- Polyglot Semantic Parsing in APIs
- Semantic Evaluation for Text-to-SQL with Distilled Test Suites
- Cross-domain Semantic Parsing via Paraphrasing
- Multi-Module System for Open Domain Chinese Question Answering over Knowledge Base
- Exploring Neural Models for Parsing Natural Language into First-Order Logic
- Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
- Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
- Knowledge Graph Question Answering via SPARQL Silhouette Generation
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- Learning an Executable Neural Semantic Parser
- Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
- A Survey on Semantic Parsing from the perspective of Compositionality
- Dependency-based Hybrid Trees for Semantic Parsing
- A Hybrid Semantic Parsing Approach for Tabular Data Analysis
- Learning Executable Semantic Parsers for Natural Language Understanding
- Compositional pre-training for neural semantic parsing
- Sentence Rewriting for Semantic Parsing
- Grounded Graph Decoding Improves Compositional Generalization in Question Answering
- MK-SQuIT: Synthesizing Questions using Iterative Template-filling
- World Knowledge as Indirect Supervision for Document Clustering