A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing
| Autor: | Xipeng Qiu, Zhifeng Hu, Mengxiao Lin, Danlu Chen |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Cross lingual
Computer science business.industry Training methods computer.software_genre Task (project management) Linguistic typology Set (abstract data type) Simple (abstract algebra) Dependency grammar Artificial intelligence Joint (audio engineering) business computer Natural language processing |
| Zdroj: | CoNLL Shared Task (2) |
| DOI: | 10.18653/v1/k18-2026 |
| Popis: | This paper describes Fudan’s submission to CoNLL 2018’s shared task Universal Dependency Parsing. We jointly train models when two languages are similar according to linguistic typology and then ensemble the models using a simple re-parse algorithm. We outperform the baseline method by 4.4% (2.1%) on average on development (test) set in CoNLL 2018 UD Shared Task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|