Learning Dependency-Based Compositional Semantics
arXiv:1109.6841
Abstract
Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of facts. The core part of such a system is the semantic parser that maps questions to logical forms. Semantic parsers are typically trained from examples of questions annotated with their target logical forms, but this type of annotation is expensive. Our goal is to learn a semantic parser from question-answer pairs instead, where the logical form is modeled as a latent variable. Motivated by this challenging learning problem, we develop a new semantic formalism, dependency-based compositional semantics (DCS), which has favorable linguistic, statistical, and computational properties. We define a log-linear distribution over DCS logical forms and estimate the parameters using a simple procedure that alternates between beam search and numerical optimization. On two standard semantic parsing benchmarks, our system outperforms all existing state-of-the-art systems, despite using no annotated logical forms.
References in corpus (1)
Cited by in corpus (34)
- Improving Text-to-SQL Evaluation Methodology
- A Syntactic Neural Model for General-Purpose Code Generation
- A Joint Model of Language and Perception for Grounded Attribute Learning
- TEQUILA: Temporal Question Answering over Knowledge Bases
- Neural Programmer: Inducing Latent Programs with Gradient Descent
- Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
- IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
- Data Recombination for Neural Semantic Parsing
- SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
- Learning Structured Natural Language Representations for Semantic Parsing
- Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism
- Semantic Parsing with Syntax- and Table-Aware SQL Generation
- Transfer Learning for Neural Semantic Parsing
- Building a Neural Semantic Parser from a Domain Ontology
- Why Build an Assistant in Minecraft?
- Toward Code Generation: A Survey and Lessons from Semantic Parsing
- Mapping to Declarative Knowledge for Word Problem Solving
- Representing Meaning with a Combination of Logical and Distributional Models
- ARSENAL: Automatic Requirements Specification Extraction from Natural Language
- Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
- Question Generation from SQL Queries Improves Neural Semantic Parsing
- Weakly-supervised Neural Semantic Parsing with a Generative Ranker
- SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases
- Left-corner Methods for Syntactic Modeling with Universal Structural Constraints
- Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations
- Joint Video and Text Parsing for Understanding Events and Answering Queries
- Dependency-based Hybrid Trees for Semantic Parsing
- Learning an Executable Neural Semantic Parser
- Learning Executable Semantic Parsers for Natural Language Understanding
- Neural Compositional Denotational Semantics for Question Answering
- Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings
- Semantic Graph Parsing with Recurrent Neural Network DAG Grammars