---

page_id: paper-bioelx kind: paper language: zh-CN source_id: src-cnbben-19b8d31c3189 source_path: papers/CNBEN/BioELX/BioELX Read Deep.md claim_id: clm-bioelx-001 claim_status: source_fact

BioELX Read Deep

一句话回忆

Model / method: BioELX, a two-stage cross-lingual BEL framework that requires no task-specific annotated training corpora.

研究卡

• 研究问题：However, expert-annotated training data for BEL are costly, especially for low-resource languages. Moreover, many cross-lingual BEL systems rely on SapBERT-based retrievers trained on predominantly English aliases in the KB, leading to poor generalization to unseen non-English mentions and limited context-aware disambiguation.
• 核心方法：BioELX, a two-stage cross-lingual BEL framework that requires no task-specific annotated training corpora.
• 主要结果：Experiments on five benchmarks (XL-BEL, EMEA, Patent, WikiMed-DE, and MedMentions) show that BioELX achieves new stateof-the-art performance
• 数据集：待补证据
• Baseline：待补证据
• 指标：待补证据
• 局限：待补证据

对当前课题的作用

• 待根据原始笔记中明确的 Relation to this project 或研究计划证据补充；当前不作无证据推断。

关键问答

<details><summary>BioELX Read Deep 的核心方法是什么？</summary>

BioELX, a two-stage cross-lingual BEL framework that requires no task-specific annotated training corpora.

</details>

字段证据

• 一句话回忆：papers/CNBEN/BioELX/BioELX Read Deep.md（line:38；clm-bioelx-005）
• 研究问题：papers/CNBEN/BioELX/BioELX Read Deep.md（line:39；clm-bioelx-002）
• 核心方法：papers/CNBEN/BioELX/BioELX Read Deep.md（line:38；clm-bioelx-003）
• 主要结果：papers/CNBEN/BioELX/BioELX Read Deep.md（line:41；clm-bioelx-004）

证据

• papers/CNBEN/BioELX/BioELX Read Deep.md（source_id: src-cnbben-19b8d31c3189）