Zero-shot Named Entity Recognition (NER)
4 papers with code • 4 benchmarks • 4 datasets
Named Entity Recognition is Zero-shot Settings. The model has not been trained in the specific dataset
WikiEvents
CrossNER
Broad Twitter Corpus
Most implemented papers
Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning
osainz59/Ask2Transformers
•
•
Findings (NAACL) 2022
In this work we show that entailment is also effective in Event Argument Extraction (EAE), reducing the need of manual annotation to 50% and 20% in ACE and WikiEvents respectively, while achieving the same performance as with full training.
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Large language models have unlocked strong multi-task capabilities from reading instructive prompts.
GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
In this paper, we propose GoLLIE (Guideline-following Large Language Model for IE), a model able to improve zero-shot results on unseen IE tasks by virtue of being fine-tuned to comply with annotation guidelines.
Rethinking Negative Instances for Generative Named Entity Recognition
yyding1/gner
•
•
In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema.
