Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Universal Dependency Parsing from Scratch

About

This paper describes Stanford's system at the CoNLL 2018 UD Shared Task. We introduce a complete neural pipeline system that takes raw text as input, and performs all tasks required by the shared task, ranging from tokenization and sentence segmentation, to POS tagging and dependency parsing. Our single system submission achieved very competitive performance on big treebanks. Moreover, after fixing an unfortunate bug, our corrected system would have placed the 2nd, 1st, and 3rd on the official evaluation metrics LAS,MLAS, and BLEX, and would have outperformed all submission systems on low-resource treebank categories on all metrics by a large margin. We further show the effectiveness of different model components through extensive ablation studies.

Peng Qi, Timothy Dozat, Yuhao Zhang, Christopher D. Manning• 2019

Related benchmarks

TaskDatasetResultRank
Dependency ParsingCoNLL UD Shared Task big treebanks 2018 2.0 (dev)
LAS (Labeled Attachment Score)83.03
8
Dependency ParsingUniversal Dependencies Low-Res treebanks (test)--
8
Universal Dependency ParsingCoNLL Shared Task all treebanks 2018 (test)
UPOS Accuracy89.95
5
Dependency ParsingUniversal Dependencies (UD) Small 3,000 token target treebank 1.0 (test)--
3
Dependency ParsingUniversal Dependencies PUD treebanks (test)
LAS (F1)82.25
2
Universal Dependency ParsingCoNLL Shared Task Big treebanks 2018 (test)
Token Accuracy99.43
2
Showing 6 of 6 rows

Other info

Code

Follow for update