Abstract syntax tree ≈ Abstract syntax tree
View article
A Syntactic Neural Model for General-Purpose Code Generation Open
We consider the problem of parsing natural language descriptions into source code written in a general-purpose programming language like Python. Existing data-driven methods treat this problem as a language generation task without consider…
View article
Convolutional Neural Networks over Tree Structures for Programming Language Processing Open
Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community. However, different from a…
View article
Using Machine Learning for Vulnerability Detection and Classification Open
The work described in this paper aims at developing a machine learning based tool for automatic identification of vulnerabilities on programs (source, high level code), that uses an abstract syntax tree representation. It is based on FastS…
View article
Abstract Syntax Networks for Code Generation and Semantic Parsing Open
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs a…
View article
Bill Hillier’s Legacy: Space Syntax—A Synopsis of Basic Concepts, Measures, and Empirical Application Open
Bill Hillier’s space syntax method and theory enables us to describe the spatial properties of a sustainable city. Empirical testing of the space syntax method over time has confirmed the capacity and innovativeness of analyzing spatial re…
View article
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X Open
Large pre-trained code generation models, such as OpenAI Codex, can generate syntax-and function-correct code, making the coding of programmers more productive. In this paper, we introduce CodeGeeX, a multilingual model with 13 billion par…
View article
Traduction Non Supervisée de Langages de Programmation Open
A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to por…
View article
TreeGen: A Tree-Based Transformer Architecture for Code Generation Open
A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems. …
View article
GraphCodeBERT: Pre-training Code Representations with Data Flow Open
Pre-trained models for programming language have achieved dramatic empirical improvements on a variety of code-related tasks such as code search, code completion, code summarization, etc. However, existing pre-trained models regard a code …
View article
Deep learning similarities from different representations of source code Open
Assessing the similarity between code components plays a pivotal role in a number of Software Engineering (SE) tasks, such as clone detection, impact analysis, refactoring, etc. Code similarity is generally measured by relying on manually …
View article
Software Defect Prediction via Attention-Based Recurrent Neural Network Open
In order to improve software reliability, software defect prediction is applied to the process of software maintenance to identify potential bugs. Traditional methods of software defect prediction mainly focus on designing static code metr…
View article
Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder Open
Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. …
View article
Modeling Source Syntax for Neural Machine Translation Open
Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly in…
View article
Seml: A Semantic LSTM Model for Software Defect Prediction Open
Software defect prediction can assist developers in finding potential bugs and reducing maintenance cost. Traditional approaches usually utilize software metrics (Lines of Code, Cyclomatic Complexity, etc.) as features to build classifiers…
View article
CODIT: Code Editing With Tree-Based Neural Models Open
The way developers edit day-to-day code tends to be repetitive, often using\nexisting code elements. Many researchers have tried to automate repetitive code\nchanges by learning from specific change templates which are applied to limited\n…
View article
A deep tree-based model for software defect prediction Open
Defects are common in software systems and can potentially cause various problems to software users. Different methods have been developed to quickly predict the most likely locations of defects in large code bases. Most of them focus on d…
View article
A Unified Syntax-aware Framework for Semantic Role Labeling Open
Semantic role labeling (SRL) aims to recognize the predicate-argument structure of a sentence. Syntactic information has been paid a great attention over the role of enhancing SRL. However, the latest advance shows that syntax would not be…
View article
Retrieval-Based Neural Code Generation Open
In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to generate complex code correctly due to a lack of ability to mem…
View article
Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs Open
Code completion has become an essential component of integrated development environments. Contemporary code completion methods rely on the abstract syntax tree (AST) to generate syntactically correct code. However, they cannot fully captur…
View article
Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks Open
We present a method for automatically generating repair feedback for syntax errors for introductory programming problems. Syntax errors constitute one of the largest classes of errors (34%) in our dataset of student submissions obtained fr…
View article
Correlating Neural and Symbolic Representations of Language Open
Analysis methods which enable us to better understand the representations and\nfunctioning of neural models of language are increasingly needed as deep\nlearning becomes the dominant approach in NLP. Here we present two methods\nbased on R…
View article
Stack-propagation: Improved Representation Learning for Syntax Open
Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates.We demonstrate that a better approach is to utilize POS tags as a regularizer of learned representations.We pr…
View article
Language-Agnostic Representation Learning of Source Code from Structure and Context Open
Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structur…
View article
Automated Classification of Overfitting Patches With Statically Extracted Code Features Open
Automatic program repair (APR) aims to reduce the cost of manually fixing\nsoftware defects. However, APR suffers from generating a multitude of\noverfitting patches, those patches that fail to correctly repair the defect\nbeyond making th…
View article
Unsupervised Translation of Programming Languages Open
A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to por…
View article
code2seq: Generating Sequences from Structured Representations of Code Open
The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine transla…
View article
Getting More Out Of Syntax with PropS Open
Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences. Yet, while much semantic structure is indeed expressed by syntax, many phenomena are not easily read out of dep…
View article
Syntax in the Treetops Open
A proposal that syntax extends to the domain of discourse in making core syntax link to the conversational context. In Syntax in the Treetops, Shigeru Miyagawa proposes that syntax extends into the domain of discourse by making linkages be…
View article
Deep Learning With Customized Abstract Syntax Tree for Bug Localization Open
Given a bug report, bug localization technique can help developers automatically locate potential buggy files. Information retrieval and deep learning approaches have been applied in bug localization by extracting lexical features in bug r…
View article
Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) Open
In recent years, the software industry has invested substantial effort to improve software quality in organizations. Applying proactive software defect prediction will help developers and white box testers to find the defects earlier, and …