Research on Chinese Semantic Role Labeling Based on Ocean Big Data
- DOI
- 10.2991/eeeis-17.2017.81How to use a DOI?
- Keywords
- semantic role labeling (SRL), ocean big data, detailed.
- Abstract
Natural Language Processing has reached the stage of semantic analysis. As a tool for semantic analysis, semantic role labeling (SRL) is becoming more and more important. But the SRL is not specifically applied to the marine field in the past. So this paper is a study of SRL based on ocean big data. First of all, this paper populates and updates corpus with data from various categories of ocean. Secondly, (based on the current semantic roles,) this study makes the semantic roles more detailed. Thirdly, we decompose the multi-predicate verbs in a sentence. Finally, SRL takes advantage of the analysis of dependency parsing (DP). In this paper, 1000 sentences of various categories of ocean are selected, and 25,903 words are used to mark the semantic roles, and the accuracy of the annotation is 93.4%, which is revised by human.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Lei-Na JIANG AU - Yun-Tao QIAN AU - Yan-Jiang SUN PY - 2017/09 DA - 2017/09 TI - Research on Chinese Semantic Role Labeling Based on Ocean Big Data BT - Proceedings of the 3rd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2017) PB - Atlantis Press SP - 548 EP - 553 SN - 2352-5401 UR - https://doi.org/10.2991/eeeis-17.2017.81 DO - 10.2991/eeeis-17.2017.81 ID - JIANG2017/09 ER -