LPNER: Label Prompt for Few-shot Nested Named Entity Recognition

Jiaoyun Yang, Zhihan Zhu, Hong Ming, Lili Jiang, Ning An
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:781-796, 2025.

Abstract

Few-shot Named Entity Recognition (NER) aims to identify named entities using very little annotated data. Recently, prompt-based few-shot NER methods have demonstrated significant effectiveness. However, most existing methods employ multi-round prompts, which significantly increase time and computational costs. Furthermore, current single-round prompt methods are mainly designed for flat NER tasks and are not effective in handling nested NER tasks. Additionally, these methods do not to fully utilize the semantic information of entity labels through prompts. To address these challenges, we propose a novel Label-Prompt-based few-shot nested NER method named LPNER, which not only handles nested NER tasks but also efficiently extracts semantic information of entities through label prompts, thereby achieving more efficient and accurate NER. LPNER first designs a specialized prompt based on a span strategy to enhance label semantics and effectively combines multiple span representations using special mark to obtain enhanced span representations integrated with label semantics. Then, entity prototypes are constructed through prototype network for classifying candidate entity spans. We conducted extensive experiments on five nested datasets: ACE04, ACE05, GENIA, GermEval, and NEREL. In 1-shot and 5-shot tasks, LPNER’s F1 scores mostly outperform baseline models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-yang25a, title = {{LPNER}: {L}abel Prompt for Few-shot Nested Named Entity Recognition}, author = {Yang, Jiaoyun and Zhu, Zhihan and Ming, Hong and Jiang, Lili and An, Ning}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {781--796}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/yang25a/yang25a.pdf}, url = {https://proceedings.mlr.press/v260/yang25a.html}, abstract = {Few-shot Named Entity Recognition (NER) aims to identify named entities using very little annotated data. Recently, prompt-based few-shot NER methods have demonstrated significant effectiveness. However, most existing methods employ multi-round prompts, which significantly increase time and computational costs. Furthermore, current single-round prompt methods are mainly designed for flat NER tasks and are not effective in handling nested NER tasks. Additionally, these methods do not to fully utilize the semantic information of entity labels through prompts. To address these challenges, we propose a novel Label-Prompt-based few-shot nested NER method named LPNER, which not only handles nested NER tasks but also efficiently extracts semantic information of entities through label prompts, thereby achieving more efficient and accurate NER. LPNER first designs a specialized prompt based on a span strategy to enhance label semantics and effectively combines multiple span representations using special mark to obtain enhanced span representations integrated with label semantics. Then, entity prototypes are constructed through prototype network for classifying candidate entity spans. We conducted extensive experiments on five nested datasets: ACE04, ACE05, GENIA, GermEval, and NEREL. In 1-shot and 5-shot tasks, LPNER’s $F_1$ scores mostly outperform baseline models.} }
Endnote
%0 Conference Paper %T LPNER: Label Prompt for Few-shot Nested Named Entity Recognition %A Jiaoyun Yang %A Zhihan Zhu %A Hong Ming %A Lili Jiang %A Ning An %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-yang25a %I PMLR %P 781--796 %U https://proceedings.mlr.press/v260/yang25a.html %V 260 %X Few-shot Named Entity Recognition (NER) aims to identify named entities using very little annotated data. Recently, prompt-based few-shot NER methods have demonstrated significant effectiveness. However, most existing methods employ multi-round prompts, which significantly increase time and computational costs. Furthermore, current single-round prompt methods are mainly designed for flat NER tasks and are not effective in handling nested NER tasks. Additionally, these methods do not to fully utilize the semantic information of entity labels through prompts. To address these challenges, we propose a novel Label-Prompt-based few-shot nested NER method named LPNER, which not only handles nested NER tasks but also efficiently extracts semantic information of entities through label prompts, thereby achieving more efficient and accurate NER. LPNER first designs a specialized prompt based on a span strategy to enhance label semantics and effectively combines multiple span representations using special mark to obtain enhanced span representations integrated with label semantics. Then, entity prototypes are constructed through prototype network for classifying candidate entity spans. We conducted extensive experiments on five nested datasets: ACE04, ACE05, GENIA, GermEval, and NEREL. In 1-shot and 5-shot tasks, LPNER’s $F_1$ scores mostly outperform baseline models.
APA
Yang, J., Zhu, Z., Ming, H., Jiang, L. & An, N.. (2025). LPNER: Label Prompt for Few-shot Nested Named Entity Recognition. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:781-796 Available from https://proceedings.mlr.press/v260/yang25a.html.

Related Material