mlsanityData to 14 Oct 2026

A Study of Variable-Role-based Feature Enrichment in Neural Models of Code

arXiv 2303.04942 ↗First posted 8 Mar 2023cs.LG cs.PL cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code. The notion of variable roles (as introduced in the works of Sajaniemi et al. [Refs. 1,2]) has been found to help students' abilities in programming. In this paper, we investigate if this notion would improve the performance of neural models of code. To the best of our knowledge, this is the first work to investigate how Sajaniemi et al.'s concept of variable roles can affect neural models of code. In particular, we enrich a source code dataset by adding the role of individual variables in the dataset programs, and thereby conduct a study on the impact of variable role enrichment in training the Code2Seq model. In addition, we shed light on some challenges and opportunities in feature enrichment for neural code intelligence models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

22 of 35 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  4. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
  5. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  6. 2020Unsupervised Translation of Programming Languagescited by 263
  7. 2018code2vec: Learning Distributed Representations of Codecited by 250
  8. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 179
  9. 2020On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformationscited by 44
  10. 2021Multilingual training for Software Engineeringcited by 43
  11. 2018Aroma: Code Recommendation via Structural Code Searchcited by 29
  12. 2020InferCode: Self-Supervised Learning of Code Representations by Predicting Subtreescited by 23
10 more
  1. 2021Understanding Neural Code Intelligence Through Program Simplificationcited by 22
  2. 2020Learning Semantic Program Embeddings with Graph Interval Neural Networkcited by 20
  3. 2014Structured Generative Models of Natural Source Codecited by 19
  4. 2021Towards Learning (Dis)-Similarity of Source Code from Program Contrastscited by 17
  5. 2020Embedding Java Classes with code2vec: Improvements from Variable Obfuscationcited by 12
  6. 2021VarCLR: Variable Semantic Representation Pre-training via Contrastive Learningcited by 11
  7. 2016sk_p: a neural program corrector for MOOCscited by 10
  8. 2022Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehensioncited by 10
  9. 2020Towards Demystifying Dimensions of Source Code Embeddingscited by 9
  10. 2021Code2Snapshot: Using Code Snapshots for Learning Representations of Source Codecited by 4

Built on by

Not cited yet.