Search the digital library catalog

Abstract: Software evolution is driven by changes made during software development and maintenance. While source control systems effectively manage these changes at the commit level, the intent behind them are often inadequately documented, making understanding their rationale challenging. Existing commit intent classification approaches, largely reliant on commit messages, only partially capture the underlying intent, predominantly due to the messages’ inadequate content and neglect of the semantic nuances in code changes. This paper presents a novel method for extracting semantic features from commits based on modifications in the source code, where each commit is represented by one or more fine-grained conjoint code changes, e.g., file-level or hunk-level changes. To address the unstructured nature of code, the method leverages a pre-trained transformer-based code model, further trained through task-adaptive pre-training and fine-tuning on the downstream task of intent classification. This fine-tuned task-adapted pre-trained code model is then utilized to embed fine-grained conjoint changes in a commit, which are aggregated into a unified commit-level vector representation. The proposed method was evaluated using two BERT-based code models, i.e., CodeBERT and GraphCodeBERT, and various aggregation techniques on data from open-source Java software projects. The results show that the proposed method can be used to effectively extract commit embeddings as features for commit intent classification and outperform current state-of-the-art methods of code commit representation for intent categorization in terms of software maintenance activities undertaken by commits.
Keywords: software maintenance, code commit, mining software repositories, adaptive pre-training, fine-tuning, semantic code embedding, CodeBERT, GraphCodeBERT, classification, code intelligence
Published in DKUM: 14.08.2024; Views: 81; Downloads: 5
Full text (1,65 MB)

Abstract: With the rise of deep learning technology, the field of medical image segmentation has undergone rapid development. In recent years, convolutional neural networks (CNNs) have brought many achievements and become the consensus in medical image segmentation tasks. Although many neural networks based on U-shaped structures and methods, such as skip connections have achieved excellent results in medical image segmentation tasks, the properties of convolutional operations limit their ability to effectively learn local and global features. To address this problem, the Transformer from the field of natural language processing (NLP) was introduced to the image segmentation field. Various Transformer-based networks have shown significant performance advantages over mainstream neural networks in different visual tasks, demonstrating the huge potential of Transformers in the field of image segmentation. However, Transformers were originally designed for NLP and ignore the multidimensional nature of images. In the process of operation, they may destroy the 2D structure of the image and cannot effectively capture low-level features. Therefore, we propose a new multi-scale cross-attention method called M-VAN Unet, which is designed based on the Visual Attention Network (VAN) and can effectively learn local and global features. We propose two attention mechanisms, namely MSC-Attention and LKA-Cross-Attention, for capturing low-level features and promoting global information interaction. MSC-Attention is designed for multi-scale channel attention, while LKA-Cross-Attention is a cross-attention mechanism based on the large kernel attention (LKA). Extensive experiments show that our method outperforms current mainstream methods in evaluation metrics such as Dice coefficient and Hausdorff 95 coefficient.
Keywords: CNNs, deep learning, medical image processing, NLP, semantic segmentation
Published in DKUM: 14.03.2024; Views: 495; Downloads: 306
Full text (1,46 MB)
This document has many files! More...

Abstract: Presented doctoral dissertation describes a research work on Semantic Inference, which can be regarded as an extension of Grammar Inference. The main task of Grammar Inference is to induce a grammatical structure from a set of positive samples (programs), which can sometimes also be accompanied by a set of negative samples. Successfully applying Grammar Inference can result only in identifying the correct syntax of a language. But, when valid syntactical structures are additionally constrained with context-sensitive information the Grammar Inference needs to be extended to the Semantic Inference. With the Semantic Inference a further step is realised, namely, towards inducing language semantics. In this doctoral dissertation it is shown that a complete compiler/interpreter for small Domain-Specific Languages (DSLs) can be generated automatically solely from given programs and their associated meanings using Semantic Inference. For the purpose of this research work the tool LISA.SI has been developed on the top of the compiler/interpreter generator tool LISA that uses Evolutionary Computations to explore and exploit the enormous search space that appears in Semantic Inference. A wide class of Attribute Grammars has been learned. Using Genetic Programming approach S-attributed and L-attributed have been inferred successfully, while inferring Absolutely Non-Circular Attribute Grammars (ANC-AG) with complex dependencies among attributes has been achieved by integrating a Memetic Algorithm (MA) into the LISA.SI tool.
Keywords: Grammatical Inference, Semantic Inference, Genetic Programming, Attribute Grammars, Memetic Algorithm, Domain-Specific Languages
Published in DKUM: 17.02.2022; Views: 1273; Downloads: 125
Full text (3,59 MB)

Abstract: V diplomski nalogi smo se ukvarjali s primerjavo in ovrednotenjem ogrodij CSS. Ta ogrodja so bila Bulma CSS, Foundation in Semantic UI. Najprej smo obrazložili, kaj razumemo pod pojmom ogrodje CSS, in našteli prednosti, slabosti in uporabnost ogrodij. V nadaljevanju smo izvedli raziskavo vsakega ogrodja, kjer smo pokazali različne lastnosti ogrodja in njegovo uporabo. Na koncu smo opravili primerjavo in ovrednotenje ogrodij. Med seboj smo jih primerjali po različnih kriterijih in glede na podporo, ki jo njihovi razvijalci nudijo.
Keywords: ogrodja CSS, Bulma CSS, Foundation, Semantic UI
Published in DKUM: 22.11.2019; Views: 1000; Downloads: 105
Full text (768,39 KB)

Abstract: Background and purpose: Although employee share ownership (ESO) deserves of a long tradition, we still know little about employees’ perspectives about ESO. The lack of knowledge about the employees’ attitudes towards ESO is discursively filled in the ESO debate. This paper challenges that deficit by carrying out a semantic analysis of the literature with the aim to identify the various actor constructions used implicitly in the ESO discourse. Design/Methodology/Approach: We conduct a semantic analysis of the ESO discourse. To unfold the order of this discourse we draw on the distinction between surface and underlying structure of communication in the sense of Michel Foucault. We interpret some semantic lead differences, a term coined by Niklas Luhmann, to constitute the underlying structure of communication. Results: We can identify six different streams on the ESO discourse’s surface level each defined by the ends pursued. The discourse’s underlying structure is made up of the distinctions production-consumption, capital-labour, and ownership-control that also determine the actor models implicitly in use. Conclusion: We can identify five different actor models implicit in the ESO discourse. While the CEE discourse differs on the surface level in as far as it is more concerned with questions of political legitimation of the privatisation process than with questions of economic efficiency, thus introducing political distinctions in the discourse rather missing in the west, it shares the underlying semantic lead differences with the Western discourse as well as the actor models anchored in those differences.
Keywords: Employee Share Ownership, discourse analysis, semantic lead distinctions, actor constructions, CEE countries
Published in DKUM: 22.01.2018; Views: 1129; Downloads: 110
Full text (657,20 KB)
This document has many files! More...