Cross-Lingual Adaptation using Structural Correspondence Learning

TL;DR

This paper extends Structural Correspondence Learning to cross-lingual adaptation, enabling transfer of classification models between languages using unlabeled data and a translation oracle, with significant improvements over translation-based baselines.

Contribution

It introduces a resource-efficient, task-specific method for cross-lingual adaptation that leverages unlabeled data and cross-lingual feature correspondences.

Findings

Significant error reduction in cross-language classification tasks.

Effective use of unlabeled data improves adaptation.

Insights into hyperparameter sensitivity and correspondence quality.

Abstract

Cross-lingual adaptation, a special case of domain adaptation, refers to the transfer of classification knowledge between two languages. In this article we describe an extension of Structural Correspondence Learning (SCL), a recently proposed algorithm for domain adaptation, for cross-lingual adaptation. The proposed method uses unlabeled documents from both languages, along with a word translation oracle, to induce cross-lingual feature correspondences. From these correspondences a cross-lingual representation is created that enables the transfer of classification knowledge from the source to the target language. The main advantages of this approach over other approaches are its resource efficiency and task specificity. We conduct experiments in the area of cross-language topic and sentiment classification involving English as source language and German, French, and Japanese as target languages. The results show a significant improvement of the proposed method over a machine translation baseline, reducing the relative error due to cross-lingual adaptation by an average of 30% (topic classification) and 59% (sentiment classification). We further report on empirical analyses that reveal insights into the use of unlabeled data, the sensitivity with respect to important hyperparameters, and the nature of the induced cross-lingual correspondences.