Simpler Context-Dependent Logical Forms via Model Projections
arXiv:1606.05378
Abstract
We consider the task of learning a context-dependent mapping from utterances to denotations. With only denotations at training time, we must search over a combinatorially large space of logical forms, which is even larger with context-dependent utterances. To cope with this challenge, we perform successive projections of the full model onto simpler models that operate over equivalence classes of logical forms. Though less expressive, we find that these simpler models are much faster and can be surprisingly effective. Moreover, they can be used to bootstrap the full model. Finally, we collected three new context-dependent semantic parsing datasets, and develop a new left-to-right parser.
arXiv comment10 pages, ACL 2016
References in corpus (6)
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Lambda Dependency-Based Compositional Semantics
- Question Answering with Subgraph Embeddings
- Compositional Semantic Parsing on Semi-Structured Tables
- Traversing Knowledge Graphs in Vector Space
- Can recursive neural tensor networks learn logical reasoning?
Cited by in corpus (15)
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
- Semantic Parsing with Syntax- and Table-Aware SQL Generation
- Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension
- An Encoder-Decoder Framework Translating Natural Language to Database Queries
- Building a Neural Semantic Parser from a Domain Ontology
- FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
- Unified Pragmatic Models for Generating and Following Instructions
- JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation
- Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base
- Ecological Semantics: Programming Environments for Situated Language Understanding
- A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos
- Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering
- A Dataset for Tracking Entities in Open Domain Procedural Text
- FANDA: A Novel Approach to Perform Follow-up Query Analysis
- Context Dependent Semantic Parsing: A Survey