In this paper, the method for knowledge graph completion based on using multi-hop reasoning is proposed. The relevance of the problem is due to the widespread use of large sparse knowledge graphs with incomplete data....
详细信息
In the design of collaborative software in a traditional way, it is often overlooked how complex user interactions become in a social context. This article presents a systematic literature review, investigating the mo...
详细信息
This article mainly studies the current situation and development trends of CCUS, which is based on journal articles indexed by Web of Science from 2013 to 2023 as the database. Firstly, the author applies the knowled...
详细信息
Stack Overflow is a widely-used community Q&A website for programming-related queries. In such a platform, providing related questions as suggestions to the users can significantly enhance their search experience....
详细信息
Recent advancements in networking, embedded systems, mobile computing, and artificial intelligence (AI) have brought renewed focus on code-size reduction. And within this domain, the sequence of optimization passes, k...
详细信息
Code summarization aims to facilitate code comprehension by automatically generating brief and informative summaries for source code. In software development, different projects often exhibit distinct characteristics....
详细信息
ISBN:
(纸本)9798350395693;9798350395686
Code summarization aims to facilitate code comprehension by automatically generating brief and informative summaries for source code. In software development, different projects often exhibit distinct characteristics. However, existing research frequently overlooks such project-specific knowledge, which may result in sub-optimal summarization performance. In this paper, we propose PRECOS, a retrieval-based method that leverages the historical examples within the project (i.e., internal corpus) for generating better code summaries. First we construct the internal corpus as a datastore, and extend the datastore by retrieving the most relevant examples for the current project from a large-scale external corpus based on the internal corpus. Then during generation, we retrieve the nearest neighbors from the datastore at each decoding step to interpolate the vanilla target-token distribution. For the retrieved neighbors, we introduce a novel locality-aware distance calibration mechanism, which calibrates the retrieval distance based on the locality of the nearest neighbors, thereby providing more accurate predictions. Experimental results demonstrate that PRECOS achieves a substantial improvement of up to 8.5 BLEU scores compared to the model before project-specific enhancement, and can generate better code summaries than other comparison methods while maintaining satisfactory results in additional storage, time overhead, and prediction speed(1).
Distributed teams have gained prominence in software companies. However, studies indicate that Distributed software Development (DSD) companies often face challenges related to high developer turnover. Conversely, oth...
详细信息
Welding data has a dual dependence on time and space. A welding defect prediction model based on Graph Convolutional Neural Network (GCN) and Long Short Term Memory Network (LSTM) is proposed to address the issue of i...
详细信息
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis. The current research mainly focuses on context-based and syntactic dependency-based approaches. However, they only consider the inherent syn...
详细信息
ISBN:
(纸本)9798400708305
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis. The current research mainly focuses on context-based and syntactic dependency-based approaches. However, they only consider the inherent syntactic connections and linguistic properties within the sentence, and much additional knowledge is not considered or utilized. To handle this concern, we propose a knowledge embedding and syntactic information enhancement network (KESE). KESE aims to fully utilize syntactic dependency and introduce external knowledge for assisting in mining the connection between aspect and sentiment words. We utilize an aspect-oriented attention mechanism to capture aspect features and enhance them with syntactic masking networks and graph convolutional networks. Furthermore, we embed knowledge graphs to improve the recognition of aspects and sentiments. We conduct experiments on several publicly accessible ABSA datasets, and the results demonstrate the effectiveness of our proposed KESE.
Context: The knowledge domain of softwareengineering (SE) gradually expands due to fast emerging technologies and complex organisational processes. The software industry represents a special focus of interest from a ...
详细信息
暂无评论