TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
arXiv:1810.02720
Abstract
We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs). TRANX uses a transition system based on the abstract syntax description language for the target MR, which gives it two major advantages: (1) it is highly accurate, using information from the syntax of the target MR to constrain the output space and model the information flow, and (2) it is highly generalizable, and can easily be applied to new types of MR by just writing a new abstract syntax description corresponding to the allowable structures in the MR. Experiments on four different semantic parsing and code generation tasks show that our system is generalizable, extensible, and effective, registering strong results compared to existing neural semantic parsers.
EMNLP 2018 (Demo Track)
References in corpus (5)
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- A Syntactic Neural Model for General-Purpose Code Generation
- Semantic Parsing with Syntax- and Table-Aware SQL Generation
Cited by in corpus (13)
- Learning to Represent Edits
- EVIL: Exploiting Software via Natural Language
- TreeGen: A Tree-Based Transformer Architecture for Code Generation
- Optimizing Deeper Transformers on Small Datasets
- Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
- Merging Weak and Active Supervision for Semantic Parsing
- LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network
- Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
- Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines
- Context Dependent Semantic Parsing: A Survey
- Few-Shot Semantic Parsing for New Predicates
- Adabot: Fault-Tolerant Java Decompiler
- Text Classification for Task-based Source Code Related Questions