期刊
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
卷 28, 期 -, 页码 2427-2437出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TASLP.2020.3016127
关键词
Syntactics; Semantics; Bit error rate; Context modeling; Labeling; Gold; Adaptation models; Natural language processing; cross-lingual transfer; semantic role labeling (SRL); model transfer
资金
- National Natural Science Foundation of China [61602160, 61772378]
- National Key Research, and Development Program of China [2017YFC1200500]
- Research Foundation of Ministry of Education of China [18JZD015, 11ZD189]
Prior studies show that cross-lingual semantic role labeling (SRL) can be achieved by model transfer under the help of universal features. In this article, we fill the gap of cross-lingual SRL by proposing an end-to-end SRL model that incorporates a variety of universal features and transfer methods. We study both the bilingual transfer and multi-source transfer, under gold or machine-generated syntactic inputs, pre-trained high-order abstract features, and contextualized multilingual word representations. Experimental results on the Universal Proposition Bank corpus indicate that performances of the cross-lingual SRL can vary by leveraging different cross-lingual features. In addition, whether the features are gold-standard also has an impact on performances. Precisely, we find that gold syntax features are much more crucial for cross-lingual SRL, compared with the automatically-generated ones. Moreover, universal dependency structure features are able to give the best help, and both pre-trained high-order features and contextualized word representations can further bring significant improvements.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据