A Multi-Perspective Architecture for Semantic Code Search

Haldar, Rajarshi; Wu, Lingfei; Xiong, Jinjun; Hockenmaier, Julia

doi:10.48550/arxiv.2005.06980

Cited by 6 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many application domains and previous studies [ 60 , 61 , 62 , 63 ] used various evaluation metrics depending on the recommender systems. To determine how effectively a recommender system performs, we used the following evaluation measures.…”

Section: Experimental Evaluationsmentioning

confidence: 99%

An Intelligent Platform for Software Component Mining and Retrieval

Bibi

Rana

Maqbool

et al. 2023

Sensors

View full text Add to dashboard Cite

The development of robotic applications necessitates the availability of useful, adaptable, and accessible programming frameworks. Robotic, IoT, and sensor-based systems open up new possibilities for the development of innovative applications, taking advantage of existing and new technologies. Despite much progress, the development of these applications remains a complex, time-consuming, and demanding activity. Development of these applications requires wide utilization of software components. In this paper, we propose a platform that efficiently searches and recommends code components for reuse. To locate and rank the source code snippets, our approach uses a machine learning approach to train the schema. Our platform uses trained schema to rank code snippets in the top k results. This platform facilitates the process of reuse by recommending suitable components for a given query. The platform provides a user-friendly interface where developers can enter queries (specifications) for code search. The evaluation shows that our platform effectively ranks the source code snippets and outperforms existing baselines. A survey is also conducted to affirm the viability of the proposed methodology.

show abstract

Section: Experimental Evaluationsmentioning

confidence: 99%

An Intelligent Platform for Software Component Mining and Retrieval

Bibi

Rana

Maqbool

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In contrast,Yao et al 23 employs a reinforcement learning framework to produce code annotations for code retrieval, and then distinguishes between relevant and non-related code snippets using the generated annotations. On the other hand, Haldar et al 18 utilizes an LSTM encoder to represent code snippets, which are generated based on both unprocessed tokens and AST-converted text sequences. For semantic code retrieval, their approach employs a bilateral multi-perspective matching model.…”

Section: Related Workmentioning

confidence: 99%

“…CAT proposed by 18 represents programming codes using unprocessed tokens with AST's sequence of strings using sequence encoders. Additionally, the authors developed a hybrid model known as MPCAT and added multi-perspective matching procedures 63 to CAT.…”

Section: Catmentioning

confidence: 99%

“…These vector representations are then utilized to compute the similarity between code snippets and queries. Subsequent approaches 14,17,[17][18][19] have emulated the DeepCS approach with minor adjustments in the encoding models. These methods rank code snippets based on the degree of resemblance between the observed distributed representations of the given query terms and code snippets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Deep Learning based Code Retrieval using Unified Graph Structure and Semantic Graph Matching Encoder

Bashir

Rahman

2023

Preprint

View full text Add to dashboard Cite

Computer programmers frequently use code retrieval systems to reuse existing code snippets from open-source repositories. These systems search a large collection of code snippets to retrieve the most relevant ones based on a text query. However, capturing semantic information between user queries and code snippets presents a key challenge in this task. Previous works have primarily used natural language processing (NLP) approaches to calculate relevance, but these approaches cannot capture deep structural and semantic dependencies between queries and snippets. In this study, we proposed a novel approach called Deep Graph-Based Semantic Representation and Matching (DeepGSR) for code retrieval. Our approach transforms queries and code snippets into a unified graph-structure representation and then retrieves relevant code snippets using a novel graph matching and retrieval approach. DeepGSR learns fine-grained relevance between queries and code snippets using cross-attention-based semantic matching operators, in addition to extracting structural information. We evaluated our approach using two publicly available code retrieval datasets, and the experiments demonstrate that DeepGSR efficiently retrieves relevant code snippets for a given query and significantly outperforms existing code retrieval approaches.

show abstract

“…A second observation is that the strong trend has been to squeeze ever more information out of the source code being E S C *Loyola et al (2017) [16] x *Lu et al (2017) [17] x *Jiang et al (2017) [18] x *Hu et al (2018) [19] x *Hu et al (2018) [9] x x *Allamanis et al (2018) [20] x x *Wan et al (2018) [21] x x *Liang et al (2018) [22] x x *Alon et al (2019) [23], [24] x x *Gao et al (2019) [25] x *LeClair et al (2019) [7] x x *Mesbah et al (2019) [26] x x *Nie et al (2019) [27] x x *Haldar et al (2020) [28] x x *Ahmad et al (2020) [29] x *Haque et al (2020) [30] x x *Zügner et al (2021) [8] x x *Liu et al (2021) [31] x x *<this paper> x x Fig. 1.…”

Section: A Source Code Summarizationmentioning

confidence: 99%

Project-Level Encoding for Neural Source Code Summarization of Subroutines

Bansal¹,

Haque²,

McMillan³

2021

Preprint

View full text Add to dashboard Cite

Source code summarization of a subroutine is the task of writing a short, natural language description of that subroutine. The description usually serves in documentation aimed at programmers, where even brief phrase (e.g. "compresses data to a zip file") can help readers rapidly comprehend what a subroutine does without resorting to reading the code itself. Techniques based on neural networks (and encoder-decoder model designs in particular) have established themselves as the state-of-the-art. Yet a problem widely recognized with these models is that they assume the information needed to create a summary is present within the code being summarized itself -an assumption which is at odds with program comprehension literature. Thus a current research frontier lies in the question of encoding source code context into neural models of summarization. In this paper, we present a project-level encoder to improve models of code summarization. By project-level, we mean that we create a vectorized representation of selected code files in a software project, and use that representation to augment the encoder of state-of-the-art neural code summarization techniques. We demonstrate how our encoder improves several existing models, and provide guidelines for maximizing improvement while controlling time and resource costs in model size.

show abstract

A Multi-Perspective Architecture for Semantic Code Search

Cited by 6 publications

References 0 publications

An Intelligent Platform for Software Component Mining and Retrieval

An Intelligent Platform for Software Component Mining and Retrieval

Efficient Deep Learning based Code Retrieval using Unified Graph Structure and Semantic Graph Matching Encoder

Project-Level Encoding for Neural Source Code Summarization of Subroutines

Contact Info

Product

Resources

About