arXiv 2502.023912025-02-04cs.CLcs.AI

FewTopNER：在多语言框架中融合少样本学习、主题建模与命名实体识别

FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework

High School of Technology Salé（萨莱高等技术学院）；Mohammed V University in Rabat（拉巴特穆罕默德五世大学）

Ibrahim Bouabdallaoui, Fatima Guerouate, Samya Bouhaddour, Chaimae Saadi, Mohammed Sbihi

备注：: Code source : https://github.com/ibrahimself/FewTopNER/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

FewTopNER 提出一种融合少样本 NER 与主题建模的多语言框架，通过共享编码器和跨任务双向注意力机制增强实体消歧，在五种语言基准上显著提升 F1 分数与主题连贯性。

摘要：

我们提出 FewTopNER，一个新颖的框架，将少样本命名实体识别（NER）与主题感知的上下文建模相结合，以应对跨语言和低资源场景中的挑战。FewTopNER 利用基于 XLM-RoBERTa 的共享多语言编码器，并辅以语言特定的校准机制，生成鲁棒的上下文嵌入。该架构包含一个基于原型的实体识别分支，采用 BiLSTM 和条件随机场进行序列标注，以及一个主题建模分支，通过混合概率与神经方法提取文档级语义特征。跨任务桥接机制促进实体表示与主题表示之间的动态双向注意力和特征融合，从而通过引入全局语义上下文增强实体消歧。在涵盖英语、法语、西班牙语、德语和意大利语的多语言基准上的实证评估表明，FewTopNER 显著优于现有的最先进少样本 NER 模型。具体而言，该框架在 F1 分数上实现了 2.5-4.0 个百分点的提升，并在以归一化点互信息衡量时展现出更高的主题连贯性。消融研究进一步证实了共享编码器和跨任务集成机制对整体性能的关键贡献。这些结果强调了将主题感知上下文纳入少样本 NER 的有效性，并凸显了 FewTopNER 在低资源环境下进行鲁棒跨语言应用的潜力。

英文摘要：

We introduce FewTopNER, a novel framework that integrates few-shot named entity recognition (NER) with topic-aware contextual modeling to address the challenges of cross-lingual and low-resource scenarios. FewTopNER leverages a shared multilingual encoder based on XLM-RoBERTa, augmented with language-specific calibration mechanisms, to generate robust contextual embeddings. The architecture comprises a prototype-based entity recognition branch, employing BiLSTM and Conditional Random Fields for sequence labeling, and a topic modeling branch that extracts document-level semantic features through hybrid probabilistic and neural methods. A cross-task bridge facilitates dynamic bidirectional attention and feature fusion between entity and topic representations, thereby enhancing entity disambiguation by incorporating global semantic context. Empirical evaluations on multilingual benchmarks across English, French, Spanish, German, and Italian demonstrate that FewTopNER significantly outperforms existing state-of-the-art few-shot NER models. In particular, the framework achieves improvements of 2.5-4.0 percentage points in F1 score and exhibits enhanced topic coherence, as measured by normalized pointwise mutual information. Ablation studies further confirm the critical contributions of the shared encoder and cross-task integration mechanisms to the overall performance. These results underscore the efficacy of incorporating topic-aware context into few-shot NER and highlight the potential of FewTopNER for robust cross-lingual applications in low-resource settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。