arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.01183cs.CL
收藏

面向低资源命名实体识别的逆向注意力知识转移

Converse Attention Knowledge Transfer for Low-Resource Named Entity Recognition

University of Science and Technology of China(中国科学技术大学);Nanyang Technological University(南洋理工大学)

Shengfei Lyu, Linghao Sun, Huixiong Yi, Yong Liu, Huanhuan Chen, Chunyan Miao

摘要:

近年来,在自然语言处理(NLP)的许多任务中取得了巨大成功,例如,命名实体识别(NER),特别是在高资源语言中,即,英语,部分归功于大量的标记资源。然而,大多数低资源语言没有像高资源英语那样丰富的标记数据,导致这些低资源语言的NER性能不佳。受知识转移的启发,我们提出了逆向注意力网络,简称CAN,通过利用在预训练的高资源英语模型中学习到的知识来提高低资源语言的NER性能。CAN首先使用基于注意力的翻译模块将低资源语言翻译成高资源英语。在翻译过程中,可以获得两种语言的注意力矩阵。此外,CAN使用注意力矩阵将来自预训练的高资源英语模型的高资源语义特征与低资源语义特征对齐。因此,CAN获得对齐的高资源语义特征,以丰富低资源语言的表示。在4个低资源NER数据集上的实验表明,CAN算法取得了一致且显著的性能提升,表明了CAN算法的有效性。

英文摘要:

In recent years, great success has been achieved in many tasks of natural language processing (NLP), e.g., named entity recognition (NER), especially in the high-resource language, i.e., English, thanks in part to the considerable amount of labeled resources. However, most low-resource languages do not have such an abundance of labeled data as high-resource English, leading to poor performance of NER in these low-resource languages. Inspired by knowledge transfer, we propose Converse Attention Network, or CAN in short, to improve the performance of NER in low-resource languages by leveraging the knowledge learned in pretrained high-resource English models. CAN first translates low-resource languages into high-resource English using an attention based translation module. In the process of translation, CAN obtain the attention matrices that align the two languages. Furthermore, CAN use the attention matrices to align the high-resource semantic features from a pretrained high-resource English model with the low-resource semantic features. As a result, CAN obtains aligned high-resource semantic features to enrich the representations of low-resource languages. Experiments on four low-resource NER datasets show that CAN achieves consistent and significant performance improvements, which indicates the effectiveness of CAN.

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。

↑