A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks
Ding, Ruiqing, Han, Xiao, Wang, Leye
–arXiv.org Artificial Intelligence
By focusing the pre-training process on domain-specific corpora, some domain-specific pre-trained language models (PLMs) have achieved state-of-the-art results. However, it is under-investigated to design a unified paradigm to inject domain knowledge in the PLM fine-tuning stage. We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs. Given domain-specific task texts input, KnowledgeDA can automatically generate a domain-specific language model following three steps: (i) localize domain knowledge entities in texts via an embedding-similarity approach; (ii) generate augmented samples by retrieving replaceable domain entity pairs from two views of both knowledge graph and training data; (iii) select high-quality augmented samples for fine-tuning via confidence-based assessment. We implement a prototype of KnowledgeDA to learn language models for two domains, healthcare and software development. Experiments on domain-specific text classification and QA tasks verify the effectiveness and generalizability of KnowledgeDA.
arXiv.org Artificial Intelligence
Jun-5-2023
- Country:
- North America > United States (0.04)
- Asia > China
- Genre:
- Research Report (1.00)
- Industry:
- Health & Medicine > Therapeutic Area (0.96)
- Technology: