Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data

2020/06/02 by Xinyu Wang, Yong Jiang, Wang, Xinyu +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.2006.01414

IWPT 2020 shared task. After fixing the bug, our proposed parser performs better than the team that ranked 1st in the official results

arxiv created 2021/06/02 · arxiv updated 2021/06/03

Abstract

This paper presents the system used in our submission to the IWPT 2020 Shared Task. Our system is a graph-based parser with second-order inference. For the low-resource Tamil corpus, we specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil. Due to our misunderstanding of the submission requirements, we submitted graphs that are not connected, which makes our system only rank 6th over 10 teams. However, after we fixed this problem, our system is 0.6 ELAS higher than the team that ranked 1st in the official results.

Related

• Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
• ThamizhiUDp: A Dependency Parser for Tamil
• Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
• Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing
• Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding