SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.11302 · 2021

Multilingual and cross-lingual document classification: A meta-learning approach

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

The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint training when limited target-language data is available during training. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state of the art on several languages while performing on-par on others, using only a small amount of labeled data.

For agents

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

get_harvested_code_for_paper("2101.11302")
get_code_for_paper("2101.11302")
have("2101.11302")

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

curl https://syntology.ai/api/ran/2101.11302.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.11302.svg)](https://syntology.ai/paper/2101.11302)

Connect an agent — have() is free.