Universal Semantic Tagging for English and Mandarin Chinese
Wenxi Li, Yiyang Hou, Yajie Ye, Li Liang, Weiwei Sun
Abstract
Universal Semantic Tagging aims to provide lightweight unified analysis for all languages at the word level. Though the proposed annotation scheme is conceptually promising, the feasibility is only examined in four Indo–European languages. This paper is concerned with extending the annotation scheme to handle Mandarin Chinese and empirically study the plausibility of unifying meaning representations for multiple languages. We discuss a set of language-specific semantic phenomena, propose new annotation specifications and build a richly annotated corpus. The corpus consists of 1100 English–Chinese parallel sentences, where compositional semantic analysis is available for English, and another 1000 Chinese sentences which has enriched syntactic analysis. By means of the new annotations, we also evaluate a series of neural tagging models to gauge how successful semantic tagging can be: accuracies of 92.7% and 94.6% are obtained for Chinese and English respectively. The English tagging performance is remarkably better than the state-of-the-art by 7.7%.
BibTeX
@inproceedings{li-etal-2021-universal,
title = "Universal Semantic Tagging for {E}nglish and {M}andarin {C}hinese",
author = "Li, Wenxi and
Hou, Yiyang and
Ye, Yajie and
Liang, Li and
Sun, Weiwei",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.440/",
doi = "10.18653/v1/2021.naacl-main.440",
pages = "5554--5566"
}