A5100677392- Topic Modeling
- Service-Oriented Architecture and Web Services
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Advanced Text Analysis Techniques
- Software Engineering Research
- Advanced Computational Techniques and Applications
- Advanced Software Engineering Methodologies
- Advanced Database Systems and Queries
- Software Engineering Techniques and Practices
- Web Data Mining and Analysis
- Biomedical Text Mining and Ontologies
- Advanced Multi-Objective Optimization Algorithms
- Data Management and Algorithms
- Data Mining Algorithms and Applications
- Algorithms and Data Compression
- Text Readability and Simplification
- Software Reliability and Analysis Research
- Sentiment Analysis and Opinion Mining
- Metaheuristic Optimization Algorithms Research
- Text and Document Classification Technologies
- Advanced Data Processing Techniques
- Advanced Clustering Algorithms Research
- Multi-Agent Systems and Negotiation
- Mobile Agent-Based Network Management
HBIS (China)
2025
University of Shanghai for Science and Technology
2024
Shanghai University of Finance and Economics
2014-2023
Hainan University
2023
Zhengzhou University of Light Industry
2022
Hangzhou Normal University
2021
Harbin University
2020-2021
Harbin Engineering University
2020-2021
University of Cincinnati
2017
Shanghai Jiao Tong University
2005-2014
Word Sense Disambiguation (WSD) has been a basic and on-going issue since its introduction in natural language processing (NLP) community. Its application lies many different areas including sentiment analysis, Information Retrieval (IR), machine translation knowledge graph construction. Solutions to WSD are mostly categorized into supervised knowledge-based approaches. In this paper, method is proposed, modeling the problem with semantic space path hidden behind given sentence. The approach...
Abstract The prediction of major histocompatibility complex (MHC)-peptide binding affinity is an important branch in immune bioinformatics, especially helpful accelerating the design disease vaccines and immunity therapy. Although deep learning-based solutions have yielded promising results on MHC-II molecules recent years, these methods ignored structure knowledge from each peptide when employing neural network models. Each sequence has its specific combination order, so it worth...
Recently, various illustrative examples have shown the impressive ability of generative large language models (LLMs) to perform NLP related tasks. ChatGPT undoubtedly is most representative model. We empirically evaluate ChatGPT's performance on requirements information retrieval (IR) tasks derive insights into designing or developing more effective methods tools based LLMs. design an evaluation framework considering four different combinations two popular IR and common artifact types. Under...
Contextual embeddings are proved to be overwhelmingly effective the task of Word Sense Disambiguation (WSD) compared with other sense representation techniques. However, these fail embed knowledge in semantic networks. In this paper, we propose a Synset Relation-Enhanced Framework (SREF) that leverages relations for both embedding enhancement and try-again mechanism implements WSD again, after obtaining basic from augmented WordNet glosses. Experiments on all-words lexical sample datasets...
The discovery of conserved sequential patterns in biological sequences is essential to unveiling common shared functions. Mining generators as well mining closed can contribute a more concise result set than all patterns, especially the analysis big data bioinformatics. Previous studies have also presented convincing arguments that generator preferable pattern inductive inference and classification. However, classic algorithms, due lack consideration on contiguous constraint along with...
The amount of information available via networks and databases highlights the limited assistance existing search retrieval engines in locating relevant information. Owing to rising demand for retrieval, manufacturers employ various techniques provide a more satisfied performance its domain. As knowledge-intensive activity, product development team seeks effective knowledge achieve competitive advantage. This paper proposes methodology using autonomous, intelligent agents transform passive...
Software requirements analysis is crucial for any software project and it the basis of reuse within Product Line engineering. specifications are usually expressed in natural language, which informal, imprecise ambiguous, thus analyzing them automatically a challenging task. Although methods towards automatic have been studied before, many limitations effective researches this area still lacking. Therefore, paper new approach was proposed to extract structured information functional from...