Pretrained language models (PLMs) have achieved impressive results and have become
vital tools for various natural language processing (NLP) tasks. However, there is a limitation …

High-quality method names are very significant for us to understand programs and maintain
software efficiently. Giving concise and consistent method names can help developers …

Transformers have shown great success in learning representations for language modelling.
However, an open challenge still remains on how to systematically aggregate semantic …

Machine learning approaches have become a crucial tool in graph analysis. Despite the
accurate results of the existing approaches, most of them are not scalable enough to be …

Document Classification has a wide range of applications in various domains like Ontology
Mapping, Sentiment Analysis, Topic Categorization and Document Clustering, to mention a …

Semantic segmentation, a fundamental job in computer vision, involves identifying and
classifying items in an image. However, it is too costly to collect a sizable volume of …

Sequence data are extensively studied in numerous domains, such as time series
forecasting, audio analysis, Natural Language Processing (NLP), Etc. However, the …

Text classification, aiming for discovering corresponding relationships between labels and
texts, is a pivotal task in Natural Language Processing (NLP). The existing joint text-label …

Most of the existing text classification methods focus on improving the feature expression of
the text, and only use the label in the final classification, while ignoring the semantic …

This paper proposes a systemic design framework GTQG (Graph Transformer Question
Generator), which generates questions based on the combination of knowledge graph and …