Challenge: Existing languages have syntactic representations of code to improve code intelligence, but they are difficult to learn from code.
Approach: They propose to embed dynamic information of programs revealed by their test cases into feature representations of code as complements.
Outcome: The proposed method yields 6%/19% mAP improvements over its masked language modeling counterparts.

Similar Papers

Understanding Programs by Exploiting (Fuzzing) Test Cases (2023.findings-acl)

Copied to clipboard

Challenge: Semantic understanding of programs has attracted great attention in the community . large language models (LLMs) are capable of learning contextual information from data at scale .
Approach: They propose to incorporate a relationship between inputs and possible outputs into learning for achieving a deeper semantic understanding of programs.
Outcome: The proposed method outperforms current state-of-the-art on two programming tasks and outperformed current state of the art by large margins.
Text-to-Code Generation with Modality-relative Pre-training (2024.eacl-long)

Copied to clipboard

Challenge: Large pre-trained language models have been applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model.
Approach: They propose to map programming language modalities into the same embedding space by separating embeddable spaces between modality and modality-relative training objectives.
Outcome: The proposed model can be adapted and represented differently depending on which modality they belong to and to the ultimate benefit of the downstream task.
Discovering Representation Sprachbund For Multilingual Pre-Training (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models perform poorly on many languages and cross-lingual tasks due to typological differences and contradictions between some languages.
Approach: They propose to pre-train multilingual pre-trained models to handle cross-lingual tasks in one model.
Outcome: The proposed model improves performance on cross-lingual tasks compared to baselines on multiple languages .
Benchmarking Language Models for Code Syntax Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models capture the syntactic rules of natural languages without fine-tuning on syntax understanding tasks.
Approach: They propose a benchmarking test to compare pre-trained language models with a large-scale dataset of programs annotated with syntactic relationships in their corresponding abstract syntax trees.
Outcome: The proposed model fails to match baselines based on positional offsets and keywords.
Contrastive Code Representation Learning (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work learns contextual representations of source code by reconstructing tokens from their context.
Approach: They propose a contrastive pre-training task that learns code functionality, not form . they propose scalable compilers that can generate variants of a program .
Outcome: The proposed task outperforms RoBERTa on an adversarial code clone detection benchmark by 39% AUROC.
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training (2022.findings-naacl)

Copied to clipboard

Challenge: Recent studies have focused on code representation learning, which aims to represent the semantics of source code into distributed vectors.
Approach: They propose to integrate different views with the natural-language description of source code into a unified framework with Multi-View contrastive Pre-training.
Outcome: The proposed model outperforms state-of-the-art models on three downstream tasks over five datasets.
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained models for Natural Languages (NL) like BERT and GPT have been shown to transfer well to Programming Languages.
Approach: They propose a unified pre-trained encoder-decoder Transformer model that leverages the code semantics conveyed from the developer-assigned identifiers.
Outcome: The proposed model outperforms existing models on understanding and generation tasks and can capture semantic information from code.
Unified Pre-training for Program Understanding and Generation (2021.naacl-main)

Copied to clipboard

Challenge: PLUG is a programming language that is used for programming and language understanding and generation tasks.
Approach: They propose a sequence-to-sequence model that performs a broad spectrum of program and language understanding and generation tasks.
Outcome: The proposed model outperforms or rivals state-of-the-art models on code summarization, code generation, and code translation tasks in seven programming languages.
UniXcoder: Unified Cross-Modal Pre-training for Code Representation (2022.acl-long)

Copied to clipboard

Challenge: Pre-trained models for programming languages have demonstrated great success on code intelligence . however, such pre-tried models are sub-optimal for auto-regressive tasks .
Approach: They propose a unified cross-modal pre-trained model for programming language that leverages cross-module contents like AST and code comment to enhance code representation.
Outcome: The proposed model achieves state-of-the-art on most code-related tasks and compares with existing models on zero-shot code-to-code search.
CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code (2023.emnlp-main)

Copied to clipboard

Challenge: NLCode generates long expressions and statements rather than a single next-token . evaluating and comparing different models has remained a challenge .
Approach: They propose a code-generating evaluation metric built on BERTScore . they use five language-specific pretrained models to evaluate their code .
Outcome: The proposed evaluation metric achieves higher correlation with human preference and functional correctness than existing metrics across four programming languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations