PulseAugur
LIVE 13:45:08
research · [2 sources] ·
0
research

SAM-NER framework improves zero-shot NER by using semantic archetypes

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have introduced SAM-NER, a novel framework designed to improve zero-shot Named Entity Recognition (ZS-NER) performance, particularly when dealing with shifts in domain or schema. The system utilizes a three-stage process involving entity discovery, abstract mediation into a universal archetype space, and semantic calibration to map predictions to target domain types. Experiments on the CrossNER benchmark indicate that SAM-NER surpasses existing ZS-NER baselines in cross-domain transfer scenarios. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Enhances zero-shot NER capabilities, potentially improving performance in specialized domains without extensive retraining.

RANK_REASON The cluster contains a research paper detailing a new framework for zero-shot Named Entity Recognition.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Ruichu Cai, Juntao Gan, Miao Mai, Zhifeng Hao, Boyan Xu ·

    SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition

    arXiv:2605.03706v1 Announce Type: new Abstract: Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intrinsic semantic organization. As a result, directly m…

  2. arXiv cs.CL TIER_1 · Boyan Xu ·

    SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition

    Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intrinsic semantic organization. As a result, directly mapping entity mentions to fine-grained target la…

RELATED ENTITIES

RELATED TOPICS