Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
Preprint
Abstract
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Towards Continual Knowledge Graph Embedding via Incremental DistillationProceedings of the AAAI Conference on Artificial Intelligence, 2024
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and ContextProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Unify Named Entity Recognition Scenarios via Contrastive Real-Time Updating PrototypeProceedings of the AAAI Conference on Artificial Intelligence, 2024
- OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement LearningProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Online Noisy Continual Relation LearningProceedings of the AAAI Conference on Artificial Intelligence, 2023
- fmLRE: A Low-Resource Relation Extraction Model Based on Feature Mapping Similarity CalculationProceedings of the AAAI Conference on Artificial Intelligence, 2023
- IterDE: An Iterative Knowledge Distillation Framework for Knowledge Graph EmbeddingsProceedings of the AAAI Conference on Artificial Intelligence, 2023
- RETRACTED: Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual GuidanceProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Using the Averaged Hausdorff Distance as a Performance Measure in Evolutionary Multiobjective OptimizationIEEE Transactions on Evolutionary Computation, 2012
- Modeling Relations and Their Mentions without Labeled Text2010