Contrastive Language Adaptation for Cross-Lingual Stance Detection

TL;DR

This paper presents a contrastive language adaptation method for cross-lingual stance detection that aligns stances across languages using memory networks, especially effective with limited labeled data.

Contribution

It introduces a novel contrastive adaptation approach applied to memory networks for improved cross-lingual stance detection.

Findings

Effective alignment of stances across languages

Outperforms current state-of-the-art methods

Works well with limited labeled data

Abstract

We study cross-lingual stance detection, which aims to leverage labeled data in one language to identify the relative perspective (or stance) of a given document with respect to a claim in a different target language. In particular, we introduce a novel contrastive language adaptation approach applied to memory networks, which ensures accurate alignment of stances in the source and target languages, and can effectively deal with the challenge of limited labeled data in the target language. The evaluation results on public benchmark datasets and comparison against current state-of-the-art approaches demonstrate the effectiveness of our approach.