Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
Not on the map. Why?
Abstract (arXiv)
This paper presents the system used in our submission to the textitIWPT 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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 0; 2023: 1.
5 papers.
- 2021Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modelingcited by 4
- 2021TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuningcited by 3
- 2021Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddingscited by 2
- 2021The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Taskcited by 1
- 2023A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsingcited by 0
- 2023A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing21 Jun 2023
- 2021TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning14 Jul 2021
- 2021Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings6 Jul 2021
- 2021The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task5 Jul 2021
- 2021Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling16 Mar 2021