In this paper, we study semantic role labelling (SRL), a subtask of semantic parsing of natural language sentences and its application for the Vietnamese language. We present our effort in building Vietnamese PropBank, the first Vietnamese SRL corpus and a software system for labelling semantic roles of Vietnamese texts. In particular, we present a novel constituent extraction algorithm in the argument candidate identification step which is more suitable and more accurate than the common node-mapping method. | VNU Journal of Science: Comp. Science & Com. Eng., Vol. 33, No. 2 (2017) 39-58 Vietnamese Semantic Role Labelling Le-Hong Phuong1,∗, Pham Thai Hoang2, Pham Xuan Khoai2, Nguyen Thi Minh Huyen1, Nguyen Thi Luong3, Nguyen Minh Hiep3 1 VNU University of Science, 334 Nguyen Trai, Thanh Xuan, Hanoi, Vietnam 2 FPT University, Hanoi, Vietnam 3 Dalat University, Lamdong, Vietnam Abstract In this paper, we study semantic role labelling (SRL), a subtask of semantic parsing of natural language sentences and its application for the Vietnamese language. We present our effort in building Vietnamese PropBank, the first Vietnamese SRL corpus and a software system for labelling semantic roles of Vietnamese texts. In particular, we present a novel constituent extraction algorithm in the argument candidate identification step which is more suitable and more accurate than the common node-mapping method. In the machine learning part, our system integrates distributed word features produced by two recent unsupervised learning models in two learned statistical classifiers and makes use of integer linear programming inference procedure to improve the accuracy. The system is evaluated in a series of experiments and achieves a good result, an F1 score of . Our system, including corpus and software, is available as an open source project for free research and we believe that it is a good baseline for the development of future Vietnamese SRL systems. Received 27 June 2017; Revised 23 October 2017; Accepted 20 November 2017 Keywords: Distributed word representation, integer linear programming, semantic role labelling, Vietnamese, Vietnamese PropBank. * Figure 1 shows the SRL of a simple Vietnamese sentence. In this example, the arguments of the predicate giúp (helped) are labelled with their semantic roles. The meaning of the labels will be described in detail in Section . 1. Introduction In this paper, we study semantic role labelling (SRL), a subtask of semantic parsing of .
