|Title:||Chinese discourse parsing: Model and evaluation||Authors:||Lin C.-A
|Keywords:||Binarizations; Chinese text; Discourse parsing; Effective solution; Evaluation metrics; Ground truth; Implicit semantics; Neural network model; Semantics||Issue Date:||2020||Start page/Pages:||1019-1024||Source:||LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings||Abstract:||
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
|Appears in Collections:||資訊工程學系|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.