Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.01147 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911132100329472 |
|---|---|
| author | Zhang, Zhihao Lee, Sophia Yat Mei Zhang, Dong Li, Shoushan Zhou, Guodong |
| author_facet | Zhang, Zhihao Lee, Sophia Yat Mei Zhang, Dong Li, Shoushan Zhou, Guodong |
| contents | Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic features facilitate effective knowledge transfer. In contrast, for non-Latin script language (NSL), such as Chinese and Japanese, performance often degrades due to deep structural differences. To address these challenges, we propose an entity-aligned translation (EAT) approach. Leveraging large language models (LLMs), EAT employs a dual-translation strategy to align entities between NSL and English. In addition, we fine-tune LLMs using multilingual Wikipedia data to enhance the entity alignment from source to target languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01147 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective Zhang, Zhihao Lee, Sophia Yat Mei Zhang, Dong Li, Shoushan Zhou, Guodong Computation and Language Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic features facilitate effective knowledge transfer. In contrast, for non-Latin script language (NSL), such as Chinese and Japanese, performance often degrades due to deep structural differences. To address these challenges, we propose an entity-aligned translation (EAT) approach. Leveraging large language models (LLMs), EAT employs a dual-translation strategy to align entities between NSL and English. In addition, we fine-tune LLMs using multilingual Wikipedia data to enhance the entity alignment from source to target languages. |
| title | Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.01147 |