Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence

TL;DR

This paper introduces a method for cross-lingual dataless document classification tailored for languages with small Wikipedia presence, leveraging large-Wikipedia languages as bridges to improve classification accuracy without training data.

Contribution

It proposes a novel approach using language similarity and dictionary-based translation to enable effective classification for low-resource languages with minimal Wikipedia content.

Findings

Improved classification accuracy for Small-Wikipedia languages

Comparable performance to the best possible language bridges

Effective use of language similarity metrics for LWL selection

Abstract

This paper presents an approach to classify documents in any language into an English topical label space, without any text categorization training data. The approach, Cross-Lingual Dataless Document Classification (CLDDC) relies on mapping the English labels or short category description into a Wikipedia-based semantic representation, and on the use of the target language Wikipedia. Consequently, performance could suffer when Wikipedia in the target language is small. In this paper, we focus on languages with small Wikipedias, (Small-Wikipedia languages, SWLs). We use a word-level dictionary to convert documents in a SWL to a large-Wikipedia language (LWLs), and then perform CLDDC based on the LWL's Wikipedia. This approach can be applied to thousands of languages, which can be contrasted with machine translation, which is a supervision heavy approach and can be done for about 100 languages. We also develop a ranking algorithm that makes use of language similarity metrics to automatically select a good LWL, and show that this significantly improves classification of SWLs' documents, performing comparably to the best bridge possible.