Global Relational Models of Source Code

By Vincent J. Hellendoorn, Charles Sutton, Rishabh Singh, Petros Maniatis, David Bieber. 2020

257 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, background): “As labeled data is costly to prepare, various works study learning code fixers from unlabeled or synthetic data (Pu et al., 2016; Parihar et al., 2017; Ahmed et al., 2018; Pradel & Sen, 2018; Wang et al., 2018; Vasic et al., 2019; Gupta et al., 2019; Hajipour et al., 2019; Hellendoorn et al., 2020).”
GraphCodeBERT: Pre-training Code Representations with Data Flow (2020, background): “code clone detection (Wei & Li, 2017; Zhang et al., 2019; Wang et al., 2020), code summarization (Alon et al., 2018; Hu et al., 2018) and so on (Nguyen & Nguyen, 2015; Allamanis et al., 2018; Hellendoorn et al., 2019). Nguyen & Nguyen (2015) propose an AST-based language model to support”
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2019, methodology): “Hellendoorn et al. (2020) develop a similar model concurrently with this work, where they use relation-aware self-attention to encode data ﬂow structure in source code embeddings.”
Integrating Tree Path in Transformer for Code Representation (2021, background): “Several works [Shen et al., 2018, Shiv and Quirk, 2019] proposed new architectures for modeling tree structures, including in the domain of natural languages processing [Wang et al., 2019] and code representation learning [Hellendoorn et al., 2019, Zügner et al., 2021].”
Patching as Translation: the Data and the Metaphor (2020, background): ““aware" of which tokens to repair by biasing the decoder’s attention to the buggy tokens using the same biasing mechanism as in [13], in this case with a simple unary relation (i.”
Teaching Temporal Logics to Neural Networks (2020, background): “, 2018) or variable naming and misuse (Hellendoorn et al., 2020).”
Deep Just-In-Time Inconsistency Detection Between Comments and Source Code (2020, methodology): “erform the CodeBERT BOW (C, M) baseline and sig2More complex hybrid approaches for combining sequence and graph representations did not help for our task (Fernandes, Allamanis, and Brockschmidt 2019; Hellendoorn et al. 2020). niﬁcantly underperform all just-in-time models, including the simple rule-”
Do Transformers Really Perform Bad for Graph Representation? (2021, background): “Model variants built upon Transformer have also been shown great performance in computer vision [12, 36] and programming language [19, 57, 41].”
Mathematical Reasoning via Self-supervised Skip-tree Training (2020, methodology): “Transformer models for program understanding have focused on providing inductive biases in the architecture [Shiv and Quirk, 2019, Hellendoorn et al., 2020], whereas this work suggests to use a modiﬁed language modeling proxy task.”
Do Transformers Really Perform Badly for Graph Representation? (2021, background): “Model variants built upon Transformer have also been shown great performance in computer vision [12, 36] and programming language [19, 56, 40].”
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks (2020, methodology): “Recently machine learning has broadened the capabilities of static analysis, offering progress on challenging problems like code completion [5], bug finding [2, 13], and program repair [25].”
Neural Edit Completion (2020, unknown): “…line of work represent programs as graphs – these usually augment the AST of a program with additional semantic edges and use a graph neural network to learn from the resulting graph [Allamanis et al. 2018; Brockschmidt et al. 2019; Fernandes et al. 2019; Hellendoorn et al. 2020; Yin et al. 2019].”
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning (2021, background): “Closely related, Hellendoorn et al. (2020) have shown that it can be helpful to hard-code the tree structure of programs in the attention mask of transformers.”
MISIM: An End-to-End Neural Code Similarity System (2020, methodology): “epresenting lexical ordering and semantic relations between the nodes. Dinella et al. (2020) also use a AST-backboned graph representation of programs to learn bug ﬁxing through graph transformation. Hellendoorn et al. (2020) introduce a simpliﬁed graph containing only AST leaf nodes for program rep”