Semantic Scaffolds for Pseudocode-to-Code Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for program generation use lightweight structures to represent high-level semantics and syntactic composition of a program.
Approach: They propose a method for program generation based on semantic scaffolds . they use line-level natural language pseudocode annotations to search for programs .
Outcome: The proposed method achieves 10% improvement in top-100 accuracy over the current state-of-the-art method.

Similar Papers

Syntactic Scaffolds for Semantic Structures (D18-1)

Copied to clipboard

Challenge: Syntactic scaffolds avoid expensive syntactical processing at runtime . many systems have used syntastic dependency or phrase-based parsers as preprocessing for semantic analysis.
Approach: They propose a multitask learning approach that uses a syntactic treebank to integrate syntaktic information into semantic tasks.
Outcome: The proposed method improves on PropBank semantics, frame semantics and coreference resolution tasks.
Natural Language Annotations for Reasoning about Program Semantics (2023.findings-emnlp)

Copied to clipboard

Challenge: Xu et al., 2022) and Tafjord eet . al. 2021) have shown that programming assistants can explain their work by grounding natural language inference in code.
Approach: They propose a dataset and protocol for annotating programs with natural language predicates at a finer granularity than code comments without relying on internal compiler representations.
Outcome: The proposed method can be used to ground natural language inference in code without static analysis and without internal compiler representations.
Analysis of Tree-Structured Architectures for Code Generation (2021.findings-acl)

Copied to clipboard

Challenge: Code generation is the task of generating code snippets from input user specifications written in natural language (NL).
Approach: They evaluate the significance of input parse trees for code generation by using constituency-based parsers as input and an abstract syntax tree as the target.
Outcome: The proposed models on a Python-based code generation dataset and a semantic parsing dataset show that constituency trees encoded using a structure-aware model improve performance.
Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic Parsing (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for table fact verification do not study generating latent programs from statements . current weakly supervised methods are limited due to huge search space with lots of spurious programs.
Approach: They propose a structure-aware approach to do table fact verification by structure-based parsing . they leverage lexical features and structure features to generate program from statements .
Outcome: The proposed method generates programs more accurately than existing parsers and achieves comparable performance to the SOTA on the large-scale benchmark TABFACT.
CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow (2024.findings-acl)

Copied to clipboard

Challenge: Comprising 3,402 crafted examples, our dataset is designed for both model finetuning and standalone evaluation.
Approach: They propose a dataset that provides examples that include a clarified intent, code snippets associated, and an average of three related unit tests.
Outcome: The proposed dataset includes 3,402 hand-written examples and 3,121 unrefined examples.
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space.
Approach: They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations.
Outcome: The proposed framework outperforms baselines while maintaining reasonable time and computational costs.
ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Despite the critical role of software requirements, these criteria have not been studied actively in previous code generation works.
Approach: They propose a framework that leverages in-context learning to organize and extrapolate unexpressed requirements from textual descriptions.
Outcome: The proposed framework generates functional requirements from textual descriptions and extrapolates unexpressed requirements from them.
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code.
Approach: They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages .
Outcome: The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation.
Factorising AMR generation through syntax (N19-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic annotation framework which abstracts away from the surface form of text to capture the core 'who did what to whom' structure.
Approach: They propose to decompose the generation process into two steps: first generate a syntactic structure, and then generate the surface form.
Outcome: The proposed approach generates meaning-preserving syntactic paraphrases of the same graph, as judged by humans.
PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation (2025.coling-main)

Copied to clipboard

Challenge: Using large language models to generate code has shown significant promise, but selecting effective examples to improve generation quality remains a challenging task.
Approach: They propose a framework that utilizes algorithmic plans to identify and retrieve effective examples.
Outcome: The proposed framework outperforms the state-of-the-art RAG methods in code generation even when the source and target languages match or differ.

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