Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing

2018-10-01CONLL 2018Code Available0· sign in to hype

Zuchao Li, Shexia He, Zhuosheng Zhang, Hai Zhao

Code Available — Be the first to reproduce this paper.

Code

github.com/bcmi220/joint_stackptr
OfficialIn paperpytorch★ 0

Abstract

This paper describes the system of team LeisureX in the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system predicts the part-of-speech tag and dependency tree jointly. For the basic tasks, including tokenization, lemmatization and morphology prediction, we employ the official baseline model (UDPipe). To train the low-resource languages, we adopt a sampling method based on other richresource languages. Our system achieves a macro-average of 68.31\% LAS F1 score, with an improvement of 2.51\% compared with the UDPipe.

Tasks

Dependency Parsing Lemmatization Part-Of-Speech Tagging POS TAG Transition-Based Dependency Parsing

Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing

Code

Abstract

Tasks

Reproductions