A Syntactic Neural Model for General-Purpose Code Generation

@inproceedings{Yin2017ASN,
  title={A Syntactic Neural Model for General-Purpose Code Generation},
  author={Pengcheng Yin and Graham Neubig},
  booktitle={ACL},
  year={2017}
}
We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python. [...] Key Result Experiments find this an effective way to scale up to generation of complex programs from natural language descriptions, achieving state-of-the-art results that well outperform previous code generation and semantic parsing approaches.Expand
Toward Code Generation: A Survey and Lessons from Semantic Parsing
TLDR
An overview of the growing body of research in semantic parsing works from an evolutionary perspective, with specific analyses on neuro-symbolic methods, architecture, and supervision is presented. Expand
Retrieval-Based Neural Code Generation
TLDR
Recode, a method based on subtree retrieval that makes it possible to explicitly reference existing code examples within a neural code generation model, is introduced. Expand
Neural Semantic Parsing for Syntax-Aware Code Generation
I Abstract The task of mapping natural language expressions to logical forms is referred to as semantic parsing. The syntax of logical forms that are based on programming or query languages, such asExpand
Program Synthesis and Semantic Parsing with Learned Code Idioms
TLDR
PATOIS is a system that allows a neural program synthesizer to explicitly interleave high-level and low-level reasoning at every generation step, and it accomplishes this by automatically mining common code idioms from a given corpus and incorporating them into the underlying language for neural synthesis. Expand
TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
TLDR
TRANX is a transition-based neural semantic parser that maps natural language utterances into formal meaning representations (MRs) and is highly generalizable, extensible, and effective, registering strong results compared to existing neural semantic parsers. Expand
TreeGen: A Tree-Based Transformer Architecture for Code Generation
TLDR
This paper proposes a novel tree-based neural architecture, TreeGen, that uses the attention mechanism of Transformers to alleviate the long-dependency problem, and introduces a novel AST reader (encoder) to incorporate grammar rules and AST structures into the network. Expand
Constrained Language Models Yield Few-Shot Semantic Parsers
TLDR
With a small amount of data and very little code to convert into English-like representations, this work provides a blueprint for rapidly bootstrapping semantic parsers and demonstrates good performance on multiple tasks. Expand
A Grammar-Based Structural CNN Decoder for Code Generation
TLDR
This paper proposes a grammar-based structural convolutional neural network (CNN) for code generation, which generates a program by predicting the grammar rules of the programming language; it designs several CNN modules, including the tree-based convolution and pre-order convolution, whose information is further aggregated by dedicated attentive pooling layers. Expand
Neural Sketch Learning for Conditional Program Generation
TLDR
This work trains a neural generator not on code but on program sketches, or models of program syntax that abstract out names and operations that do not generalize across programs, and shows that it can often predict the entire body of a method given just a few API calls or data types that appear in the method. Expand
A Syntax-Guided Neural Model for Natural Language Interfaces to Databases
TLDR
This work adapts the model of [1] to the Natural Language Interface to Databases (NLIDB) problem by taking into account the database schema, and evaluates the model on the recently introduced WIKISQL and SENLIDB datasets. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 56 REFERENCES
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
TLDR
This work presents an approach that learns to map natural-language descriptions of simple “if-then” rules to executable code by training and testing on a large corpus of naturally-occurring programs and their natural language descriptions. Expand
Language to Logical Form with Neural Attention
TLDR
This paper presents a general method based on an attention-enhanced encoder-decoder model that encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors. Expand
From Natural Language Specifications to Program Input Parsers
TLDR
A Bayesian generative model is used to capture relevant natural language phenomena and translate the English specification into a specification tree, which is then translated into a C++ input Parsers based on the correlation between the text and the specification tree. Expand
Bimodal Modelling of Source Code and Natural Language
TLDR
The aim is to bring together recent work on statistical modelling of source code and work on bimodal models of images and natural language to build probabilistic models that jointly model short natural language utterances and source code snippets. Expand
Structured Generative Models of Natural Source Code
TLDR
A family of generative models for NSC that have three key properties: first, they incorporate both sequential and hierarchical structure, second, they learn a distributed representation of source code elements, and third, they integrate closely with a compiler. Expand
Using Semantic Unification to Generate Regular Expressions from Natural Language
TLDR
This model substantially outperforms a state-of-the-art semantic parsing baseline, yielding a 29% absolute improvement in accuracy. Expand
Driving Semantic Parsing from the World’s Response
TLDR
This paper develops two novel learning algorithms capable of predicting complex structures which only rely on a binary feedback signal based on the context of an external world and reformulates the semantic parsing problem to reduce the dependency of the model on syntactic patterns, thus allowing the parser to scale better using less supervision. Expand
Latent Predictor Networks for Code Generation
TLDR
A novel neural network architecture is presented which generates an output sequence conditioned on an arbitrary number of input functions and allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to be marginalised, thus permitting scalable and effective training. Expand
Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
TLDR
A learning algorithm is described that takes as input a training set of sentences labeled with expressions in the lambda calculus and induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. Expand
Sequence-based Structured Prediction for Semantic Parsing
TLDR
An approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query and shows how grammatical constraints on the derivation sequence can easily be integrated inside the RNN-based sequential predictor. Expand
...
1
2
3
4
5
...