A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis

TL;DR

This paper introduces KEAM, a novel cross-lingual structured sentiment analysis model that leverages both implicit and explicit linguistic knowledge to improve transfer across languages, outperforming existing unsupervised methods.

Contribution

The paper proposes a knowledge-enhanced adversarial model combining an embedding adapter and syntax GCN encoder for improved cross-lingual sentiment analysis.

Findings

KEAM outperforms all unsupervised baselines on five datasets.

The model effectively captures implicit semantic information.

Explicit syntax transfer enhances cross-lingual performance.

Abstract

Structured sentiment analysis, which aims to extract the complex semantic structures such as holders, expressions, targets, and polarities, has obtained widespread attention from both industry and academia. Unfortunately, the existing structured sentiment analysis datasets refer to a few languages and are relatively small, limiting neural network models' performance. In this paper, we focus on the cross-lingual structured sentiment analysis task, which aims to transfer the knowledge from the source language to the target one. Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer. First, we design an adversarial embedding adapter for learning an informative and robust representation by capturing implicit semantic information from diverse multi-lingual embeddings adaptively. Then, we propose a syntax GCN encoder to transfer the explicit semantic information (e.g., universal dependency tree) among multiple languages. We conduct experiments on five datasets and compare \texttt{KEAM} with both the supervised and unsupervised methods. The extensive experimental results show that our \texttt{KEAM} model outperforms all the unsupervised baselines in various metrics.