https://scholars.lib.ntu.edu.tw/handle/123456789/581360
標題: | Chinese discourse parsing: Model and evaluation | 作者: | Lin C.-A Hung S.-S Huang H.-H HSIN-HSI CHEN |
關鍵字: | Binarizations; Chinese text; Discourse parsing; Effective solution; Evaluation metrics; Ground truth; Implicit semantics; Neural network model; Semantics | 公開日期: | 2020 | 起(迄)頁: | 1019-1024 | 來源出版物: | LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings | 摘要: | Chinese discourse parsing, which aims to identify the hierarchical relationships of Chinese elementary discourse units, has not yet a consistent evaluation metric. Although Parseval is commonly used, variations of evaluation differ from three aspects: micro vs. macro F1 scores, binary vs. multiway ground truth, and left-heavy vs. right-heavy binarization. In this paper, we first propose a neural network model that unifies a pre-trained transformer and CKY-like algorithm, and then compare it with the previous models with different evaluation scenarios. The experimental results show that our model outperforms the previous systems. We conclude that (1) the pre-trained context embedding provides effective solutions to deal with implicit semantics in Chinese texts, and (2) using multiway ground truth is helpful since different binarization approaches lead to significant differences in performance. ? European Language Resources Association (ELRA), licensed under CC-BY-NC |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096621390&partnerID=40&md5=6a63bb13516fa3cf21ae00a1be2e5a2a https://scholars.lib.ntu.edu.tw/handle/123456789/581360 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。