SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.08122 · EMNLP · 2021

Revisiting Tri-training of Dependency Parsers

Joachim Wagner, Jennifer Foster

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore languagespecific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tritraining but that the two approaches can be successfully combined.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.08122")
get_code_for_paper("2109.08122")
have("2109.08122")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.08122.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.08122.svg)](https://syntology.ai/paper/2109.08122)

Connect an agent — have() is free.