TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Dependency Parsing	Universal Dependencies	HIT-SCIR	LAS	75.84	# 3

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-better-ud-parsing-deep-contextualized/dependency-parsing-on-universal-dependencies)](https://paperswithcode.com/sota/dependency-parsing-on-universal-dependencies?p=towards-better-ud-parsing-deep-contextualized)`

Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation

CONLL 2018 · Wanxiang Che, Yijia Liu, Yuxuan Wang, Bo Zheng, Ting Liu ·

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on Stanford's winning system for the CoNLL 2017 shared task and make two effective extensions: 1) incorporating deep contextualized word embeddings into both the part of speech tagger and parser; 2) ensembling parsers trained with different initialization. We also explore different ways of concatenating treebanks for further improvements. Experimental results on the development data show the effectiveness of our methods. In the final evaluation, our system was ranked first according to LAS (75.84%) and outperformed the other systems by a large margin.