Enhancing Relational Triple Extraction in Specific Domains: Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language Models
Source abstract
Abstract
In the process of constructing domain-specific knowledge graphs, the task of relational triple extraction plays a critical role in transforming unstructured text into structured information. Existing relational triple extract... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Natural Language Processing Techniques · Advanced Graph Neural Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (46)
Show source-provided references
1. Knowledge graphs: Opportunities and challenges10.1007/s10462-023-10465-9 ↗
2. Entity extraction in low resource domains with selective pre-training of large language models
3. Domain-specific NER via retrieving correlated samples
4. Kernel methods for relation extraction
5. Exploiting syntactico-semantic structures for relation extraction
6. Incremental joint extraction of entity mentions and relations
7. Joint extraction of entities and relations based on a novel tagging scheme
8. EmRel: Joint representation of entities and embedded relations for multi-triple extraction
9. A simple but effective bidirectional framework for relational triple extraction
10. OD-RTE: A one-stage object detection framework for relational triple extraction
11. Joint multimodal entity-relation extraction based on edge-enhanced graph alignment network and word-pair relation tagging10.1609/aaai.v37i9.26309 ↗
12. T2G-FORMER: Organizing tabular features into relation graphs promotes heterogeneous feature interaction10.1609/aaai.v37i9.26272 ↗
13. Is ChatGPT a general-purpose natural language processing task solver?
14. Retrieval-augmented recommender system: Enhancing recommender systems with large language models
15. Large language model is not a good few-shot information extractor, but a good reranker for hard samples!
16. Table filling multi-task recurrent neural network for joint entity and relation extraction
17. Going out on a limb: Joint extraction of entity mentions and relations without dependency trees
18. Extracting relational facts by an end-to-end neural model with copy mechanism
19. A novel cascade binary tagging framework for relational triple extraction
20. TDEER: An efficient translating decoding schema for joint extraction of entities and relations
21. TPLinker: Single-stage joint extraction of entities and relations through token pair linking
22. A Frustratingly easy approach for entity and relation extraction
23. Span-based joint entity and relation extraction with transformer pre-training
24. PRGC: Potential relation and global correspondence based joint relational triple extraction
25. UniRE: A unified label space for entity relation extraction
26. Document-Level relation extraction via pair-aware and entity-enhanced representation learning
27. OneRel: Joint entity and relation extraction with one module in one step
28. Unified representation and interaction for joint relational triple extraction
29. Enhanced language representation with label knowledge for span extraction
30. Language models are few-shot learners
31. Training language models to follow instructions with human feedback
32. R. Martínez-Cruz, A. J. López-López, and J. Portela, “ChatGPT vs state-of-the-art models: A benchmarking study in keyphrase generation task,” arXiv preprint arXiv:2304.14177, Apr. 2023.10.1007/s10489-024-05901-4 ↗
33. Is ChatGPT good at search? investigating large language models as re-ranking agents
34. X. Wei et al., “Zero-shot information extraction via chatting with ChatGPT,” arXiv preprint arXiv:2302.10205, Feb. 2023.
35. R. Tang, X. Han, X. Jiang, and X. Hu, “Does synthetic data generation of LLMs help clinical text mining?” arXiv preprint arXiv:2303.04360, Apr. 2023.
36. Can large language models be an alternative to human evaluations?
37. A survey of data augmentation approaches for NLP
38. Is GPT-3 a good data annotator?
39. Large language model as attributed training data generator: A tale of diversity and bias
40. Increasing diversity while maintaining accuracy: Text data generation with large language models and human interventions
41. BERT: Pre-training of deep bidirectional transformers for language understanding
42. Exploiting entity BIO tag embeddings and multi-task learning for relation extraction with imbalanced data
43. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction
44. A linear programming formulation for global inference in natural language tasks
45. Packed levitated marker for entity and relation extraction
46. A trigger-sense memory flow framework for joint entity and relation extraction