CLMar 15, 2017

SyntaxNet Models for the CoNLL 2017 Shared Task

arXiv:1703.04929v133 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement in dependency parsing for natural language processing researchers, offering a new baseline for shared tasks.

The paper tackles dependency parsing by introducing ParseySaurus, a baseline system for the CoNLL 2017 Shared Task, which outperforms previous state-of-the-art models by 3.47% absolute LAS across 52 treebanks.

We describe a baseline dependency parsing system for the CoNLL2017 Shared Task. This system, which we call "ParseySaurus," uses the DRAGNN framework [Kong et al, 2017] to combine transition-based recurrent parsing and tagging with character-based word representations. On the v1.3 Universal Dependencies Treebanks, the new system outpeforms the publicly available, state-of-the-art "Parsey's Cousins" models by 3.47% absolute Labeled Accuracy Score (LAS) across 52 treebanks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes