Comparative Analysis of Patent Embedding Models for Similarity Calculation
Patent SBERT-adapt-ub outperforms in patent similarity, highlighting the importance of training phase in embedding models.
Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams
Effective text sampling methods are crucial for fine-tuning language models like SBERT in text stream mining to improve performance and adapt to concept drift.
Prompt-based Graph Model for Joint Liberal Event Extraction and Event Schema Induction
Events are essential components of speech and texts, describing the changes in the state of entities. The Prompt-based Graph Model for Liberal Event Extraction (PGLEE) aims to extract events and discover event schemas simultaneously, achieving excellent performance with or without predefined event schemas.
TnT-LLM: Large Language Models for Text Mining Automation
Large Language Models (LLMs) can automate and scale text mining processes efficiently, generating accurate label taxonomies and enabling lightweight classifiers for large-scale applications.
Methods for Generating Drift in Text Streams: A Comprehensive Study
Artificially generating drift in text streams is crucial for developing text stream mining methods and evaluating the performance of incremental classifiers.
Text Mining at Scale with Large Language Models: TnT-LLM
Large Language Models (LLMs) can automate the process of taxonomy generation and text classification, improving efficiency and accuracy in text mining tasks.
© 2024 by Linnk AI