Benchmarking pre-trained text embedding models in aligning built asset information

Keyphrases

• Built Assets 100%
• Asset Data 100%
• Pre-trained Text Embedding 100%
• Text-embedding Models 100%
• Data Classification 28%
• Technical Term 28%
• Dictionary 14%
• Domain Adaptation 14%
• Handover 14%
• Comprehensive Evaluation 14%
• Data Integration 14%
• Large Animal Model 14%
• Classification System 14%
• Complex Semantics 14%
• Adaptation Techniques 14%
• Common Trends 14%
• Asset Management 14%
• Re-ranking 14%
• Promising Direction 14%
• High-score 14%
• Ad Hoc Data 14%
• Open-source Library 14%
• Text Embedding 14%
• Performance Variation 14%
• Specific Evaluation 14%
• Large-scale Pre-trained Model 14%
• Technical Concept 14%
• Text Element 14%
• Text Representation Learning 14%
• Cross-mapping 14%
• Integrated Scenarios 14%
• Instruction Tuning 14%

Computer Science

• Benchmarking 100%
• Information Asset 100%
• Data Classification 66%
• Information Retrieval 33%
• Domain Adaptation 33%
• Representation Learning 33%
• Data Integration 33%
• Asset Management 33%
• Large Language Model 33%
• Open-Source Library 33%
• Text Representation 33%
• Performance Variation 33%
• Technical Concept 33%
• Instruction Tuning 33%