Codes/Datasets/Demos

Keyphrase Extraction

• Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information [doi] [Dataset & Source Code]
• Enhancing Keyphrase Extraction from Academic Articles with their Reference Information [doi] [arXiv] [Dataset & Source Code]
• Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract [doi] [arXiv] [Dataset & Source Code]
• Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs [doi] [Dataset & Source Code]
• Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts [doi] [Dataset]
• Building a Multimodal Dataset of Academic Paper for Keyword Extraction [doi] [Dataset & Source Code]

Knowlege Entity/Knowledge Graph Construction

• Revealing the Technology Development of Natural Language Processing: A Scientific Entity-Centric Perspective [doi] [Dataset & Source Code]
• Automated Generation of Research Workflows from Academic Papers: A Full-text Mining Framework [doi] [arXiv] [Dataset & Source Code]
• Using the Full-text Content of Academic Articles to Identify and Evaluate Algorithm Entities in the Domain of Natural Language Processing [doi] [arxiv] [Demo: Algorithm Influence in NLP (1979~2015)] [Video]
• SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP [doi] [arXiv] [Dataset & Source Code]
• Quantifying the Knowledge Proximity Between Academic and Industry Research: An Entity and Semantic Perspective [doi] [arXiv] [Dataset & Source Code]
• Enhancing Academic Paper Recommendations Using Fine-Grained Knowledge Entities and Multifaceted Document Embeddings [doi] [arXiv] [Dataset & Source Code]
• Using Full-text Content of Academic Articles to Build a Methodology Taxonomy of Information Science in China [doi] [arxiv] [Demo: Methodology Taxonomy of Information Science in China]

Sentence Extraction

• Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization [doi] [Dataset & Source Code]
• Automatic Recognition and Classification of Future Work Sentences from Academic Articles in a Specific Domain [doi] [arXiv] [Dataset & Source Code]
• Automatic Generation of Highlights for Academic Paper via Prompt-based Learning. [doi] [Dataset & Source Code]

Identification of Structural Functions in Academic Articles

• Enhancing Identification of Structure Function of Academic Articles Using Contextual Information [doi] [arXiv] [Dataset & Source Code]

Summarization/Survey Generation

• SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models [doi] [arXiv] [video] [Dataset & Source Code]
• Enhancing Abstractive Summarization of Scientific Papers Using Structure Information [doi] [arXiv] [Dataset & Source Code]

Novelty Measurement/Peer Review Comment Mining

• NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment [doi] [arXiv] [Dataset & Source Code] [Information Matters]
• Automated Novelty Evaluation of Academic Paper: A Collaborative Approach Integrating Human and Large Language Model Knowledge. [doi] [Dataset & Source Code])
• SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers [doi] [Dataset & Source Code]
• Impact of large language models on peer review opinions from a fine-grained perspective: Evidence from top conference proceedings in AI [doi] [arXiv] [Dataset & Source Code]
• Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI [doi] [Dataset & Source Code]
• Exploring Novelty Differences between Industry and Academia: A Knowledge Entity-centric Perspective [doi] [arXiv] [Dataset & Source Code]
• Exploring the Relationship Between Team Institutional Composition and Novelty in Academic Papers Based on Fine-Grained Knowledge Entities [doi] [Dataset & Source Code]
• Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach [doi] [Dataset & Source Code]

Research Idea Generation

• Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies. [doi] [arXiv] [Dataset & Source Code] [Demo]

Other

• Usage Frequency and Application Variety of Research Methods in Library and Information Science: Continuous investigation from 1991 to 2021 [doi] [Demo]
• Evolution of Research Method Usage Across the Academic Careers of Library and Information Science Scholars [doi] [arXiv] [Demo]
• Automatic Generation of Highlights for Academic Paper via Prompt-based Learning [doi] [Dataset & Source Code]
• Using Hashtags to Analysis Purpose and Technology Application of Open-Source Project Related to COVID-19 [doi] [arXiv] [Dataset & Source Code]
• Using social media to explore regional cuisine preferences in China [doi] [Demo]
• Finding More Bilingual Web Pages with High Credibility via Link Analysis [URL] [Dataset & Source Code]