ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916543128928256 |
|---|---|
| author | Wang, Anbang Mei, Difei Zhang, Zhichao Bai, Xiuxiu Yao, Ran Fang, Zewen Hu, Min Cao, Zhirui Sun, Haitao Guo, Yifeng Zhou, Hongyao Guo, Yu |
| author_facet | Wang, Anbang Mei, Difei Zhang, Zhichao Bai, Xiuxiu Yao, Ran Fang, Zewen Hu, Min Cao, Zhirui Sun, Haitao Guo, Yifeng Zhou, Hongyao Guo, Yu |
| contents | This paper presents ReverseNER, a method aimed at overcoming the limitation of large language models (LLMs) in zero-shot named entity recognition (NER) tasks, arising from their reliance on pre-provided demonstrations. ReverseNER tackles this challenge by constructing a reliable example library composed of dozens of entity-labeled sentences, generated through the reverse process of NER. Specifically, while conventional NER methods label entities in a sentence, ReverseNER features reversing the process by using an LLM to generate entities from their definitions and subsequently expand them into full sentences. During the entity expansion process, the LLM is guided to generate sentences by replicating the structures of a set of specific \textsl{feature sentences}, extracted from the task sentences by clustering. This expansion process produces dozens of entity-labeled task-relevant sentences. After constructing the example library, the method selects several semantically similar entity-labeled examples for each task sentence as references to facilitate the LLM's entity recognition. We also propose an entity-level self-consistency scoring mechanism to improve NER performance with LLMs. Experiments show that ReverseNER significantly outperforms other zero-shot NER methods with LLMs, marking a notable improvement in NER for domains without labeled data, while declining computational resource consumption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_00533 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models Wang, Anbang Mei, Difei Zhang, Zhichao Bai, Xiuxiu Yao, Ran Fang, Zewen Hu, Min Cao, Zhirui Sun, Haitao Guo, Yifeng Zhou, Hongyao Guo, Yu Computation and Language Artificial Intelligence This paper presents ReverseNER, a method aimed at overcoming the limitation of large language models (LLMs) in zero-shot named entity recognition (NER) tasks, arising from their reliance on pre-provided demonstrations. ReverseNER tackles this challenge by constructing a reliable example library composed of dozens of entity-labeled sentences, generated through the reverse process of NER. Specifically, while conventional NER methods label entities in a sentence, ReverseNER features reversing the process by using an LLM to generate entities from their definitions and subsequently expand them into full sentences. During the entity expansion process, the LLM is guided to generate sentences by replicating the structures of a set of specific \textsl{feature sentences}, extracted from the task sentences by clustering. This expansion process produces dozens of entity-labeled task-relevant sentences. After constructing the example library, the method selects several semantically similar entity-labeled examples for each task sentence as references to facilitate the LLM's entity recognition. We also propose an entity-level self-consistency scoring mechanism to improve NER performance with LLMs. Experiments show that ReverseNER significantly outperforms other zero-shot NER methods with LLMs, marking a notable improvement in NER for domains without labeled data, while declining computational resource consumption. |
| title | ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.00533 |