| Paper | Code | LAS | UAS | BLEX | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing | 84.60 | 87.64 | UDPipe 2.0 + mBERT + FLAIR | 2019-08-20 | ||
| 75 Languages, 1 Model: Parsing Universal Dependencies Universally | ✓ Link | 80.43 | 85.69 | UDify | 2019-04-03 | |
| Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation | ✓ Link | 75.84 | HIT-SCIR | 2018-07-09 | ||
| Universal Dependency Parsing from Scratch | ✓ Link | 74.16 | 62.08 | 65.28 | Stanford+ | 2019-01-29 |
| Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task | 73.28 | 60.99 | 66.09 | TurkuNLP | 2018-10-01 | |
| UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task | 73.11 | 61.25 | 64.49 | UDPipe 2.0 | 2018-10-01 |