SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.02562 · EMNLP Findings · 2020

Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher

Daniel Hsu, Giannis Karamanolakis, Luis Gravano

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

Cross-lingual text classification alleviates the need for manually labeled documents in a target language by leveraging labeled documents from other languages. Existing approaches for transferring supervision across languages require expensive cross-lingual resources, such as parallel corpora, while less expensive cross-lingual representation learning approaches train classifiers without target labeled documents. In this work, we propose a cross-lingual teacher-student method, CLTS, that generates "weak" supervision in the target language using minimal cross-lingual resources, in the form of a small number of word translations. Given a limited translation budget, CLTS extracts and transfers only the most important task-specific seed words across languages and initializes a teacher classifier based on the translated seed words. Then, CLTS iteratively trains a more powerful student that also exploits the context of the seed words in unlabeled target documents and outperforms the teacher. CLTS is simple and surprisingly effective in 18 diverse languages: by transferring just 20 seed words, even a bag-of-words logistic regression student outperforms state-of-theart cross-lingual methods (e.g., based on multilingual BERT). Moreover, CLTS can accommodate any type of student classifier: leveraging a monolingual BERT student leads to further improvements and outperforms even more expensive approaches by up to 12% in accuracy. Finally, CLTS addresses emerging tasks in low-resource languages using just a small number of word translations.

For agents

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

get_harvested_code_for_paper("2010.02562")
get_code_for_paper("2010.02562")
have("2010.02562")

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

curl https://syntology.ai/api/ran/2010.02562.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.02562.svg)](https://syntology.ai/paper/2010.02562)

Connect an agent — have() is free.