Language to Logical Form with Neural Attention

Abstract

Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domain- or representation-specific. In this paper we present a general method based on an attention-enhanced encoder-decoder model. We encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors. Experimental results on four datasets show that our approach performs competitively without using hand-engineered features and is easy to adapt across domains and meaning representations.

Accepted by ACL-16

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• Teaching Machines to Read and Comprehend
• Recurrent Neural Network Regularization
• Visualizing and Understanding Recurrent Networks
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Effective Approaches to Attention-based Neural Machine Translation
• Modeling Coverage for Neural Machine Translation
• Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
• Acquiring Word-Meaning Mappings for Natural Language Interfaces
• A Deep Architecture for Semantic Parsing

Cited by in corpus (67)

• Junction Tree Variational Autoencoder for Molecular Graph Generation
• TabFact: A Large-scale Dataset for Table-based Fact Verification
• Syntax-Directed Variational Autoencoder for Structured Data
• A Comparative Survey of Recent Natural Language Interfaces for Databases
• A Syntactic Neural Model for General-Purpose Code Generation
• Tree-to-tree Neural Networks for Program Translation
• Graph Neural Networks for Natural Language Processing: A Survey
• IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
• Visual Question Answering: A Survey of Methods and Datasets
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Abstract Syntax Networks for Code Generation and Semantic Parsing
• Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems
• Latent Attention For If-Then Program Synthesis
• An End-to-end Neural Natural Language Interface for Databases
• Data Recombination for Neural Semantic Parsing
• Improving Semantic Parsing for Task Oriented Dialog
• Improving Text-to-SQL with Schema Dependency Learning
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
• Embedding API Dependency Graph for Neural Code Generation
• CraftAssist: A Framework for Dialogue-enabled Interactive Agents
• TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
• TreeGen: A Tree-Based Transformer Architecture for Code Generation
• Adversarial TableQA: Attention Supervision for Question Answering on Tables
• Neural Program Search: Solving Programming Tasks from Description and Examples
• Semantic Parsing with Syntax- and Table-Aware SQL Generation
• Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
• Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention
• Cross-domain Semantic Parsing via Paraphrasing
• Transfer Learning for Neural Semantic Parsing
• Building a Neural Semantic Parser from a Domain Ontology
• An Encoder-Decoder Framework Translating Natural Language to Database Queries
• Why Build an Assistant in Minecraft?
• Sequence to Sequence Learning for Event Prediction
• Toward Code Generation: A Survey and Lessons from Semantic Parsing
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (Short Version)
• CraftAssist Instruction Parsing: Semantic Parsing for a Minecraft Assistant
• Retrieval-Based Neural Code Generation
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• Coupling Distributed and Symbolic Execution for Natural Language Queries
• From Natural Language Instructions to Complex Processes: Issues in Chaining Trigger Action Rules
• Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
• Automated proof synthesis for propositional logic with deep neural networks
• ConvMath: A Convolutional Sequence Network for Mathematical Expression Recognition
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning
• Question Generation from SQL Queries Improves Neural Semantic Parsing
• Zero-shot Transfer Learning for Semantic Parsing
• Dependency-based Hybrid Trees for Semantic Parsing
• Learning an Executable Neural Semantic Parser
• Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
• ShopTalk: A System for Conversational Faceted Search
• Domain Adaptation for Semantic Parsing
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• Exploring Neural Methods for Parsing Discourse Representation Structures
• Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
• On Robustness of Neural Semantic Parsers
• Learning by stochastic serializations
• Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism
• Symbolic Priors for RNN-based Semantic Parsing
• Semantic Parsing: Syntactic assurance to target sentence using LSTM Encoder CFG-Decoder
• A survey of cross-lingual features for zero-shot cross-lingual semantic parsing
• Logical Parsing from Natural Language Based on a Neural Translation Model
• Context Dependent Semantic Parsing: A Survey
• Neural Architecture for Question Answering Using a Knowledge Graph and Web Corpus
• Few-Shot Semantic Parsing for New Predicates