| dc.contributor | 資科系 | |
| dc.creator (作者) | 黃瀚萱 | |
| dc.creator (作者) | Huang, Hen-Hsen | |
| dc.creator (作者) | Lin, Chuan-An | |
| dc.creator (作者) | Hung, Shyh-Shiun | |
| dc.creator (作者) | Chen, Hsin-Hsi | |
| dc.date (日期) | 2020-05 | |
| dc.date.accessioned | 4-Jun-2021 14:38:13 (UTC+8) | - |
| dc.date.available | 4-Jun-2021 14:38:13 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-Jun-2021 14:38:13 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/135519 | - |
| dc.description.abstract (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. | |
| dc.format.extent | 387570 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), European Language Resources Association, pp.1019-1024 | |
| dc.title (題名) | Chinese Discourse Parsing: Model and Evaluation | |
| dc.type (資料類型) | conference | |
