MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition

Fang, J., Wang, X., Meng, Z. , Xie, P., Huang, F. and Jiang, Y. (2023) MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition. In: 61st Annual Meeting of the Association for Computational Linguistics (ACL '23), Toronto, Canada, 9-14 July 2023, (doi: 10.18653/v1/2023.acl-long.234)

Abstract

This paper focuses on the task of cross domain few-shot named entity recognition (NER), which aims to adapt the knowledge learned from source domain to recognize named entities in target domain with only a few labeled examples. To address this challenging task, we propose MANNER, a variational memory-augmented few-shot NER model. Specifically, MANNER uses a memory module to store information from the source domain and then retrieve relevant information from the memory to augment few-shot task in the target domain. In order to effectively utilize the information from memory, MANNER uses optimal transport to retrieve and process information from memory, which can explicitly adapt the retrieved information from source domain to target domain and improve the performance in the cross domain few-shot setting. We conduct experiments on English and Chinese cross domain few-shot NER datasets, and the experimental results demonstrate that MANNER can achieve superior performance.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Fang, Jinyuan and Meng, Dr Zaiqiao
• Authors: Fang, J., Wang, X., Meng, Z., Xie, P., Huang, F., and Jiang, Y.
• College/School: College of Science and Engineering > School of Computing Science
• Copyright Holders: Copyright © 2023 Association for Computational Linguistics
• First Published: First published in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• Publisher Policy: Reproduced under a Creative Commons licence

Related URLs

• Organisation