Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction

TL;DR

This paper introduces a novel test-time code-switching framework for cross-lingual aspect sentiment triplet extraction, improving performance and setting new benchmarks with generative models and alignment techniques.

Contribution

The paper proposes a new TT-CSW framework that enhances cross-lingual ASTE by combining bilingual training with test-time augmentation, addressing boundary detection and out-of-dictionary issues.

Findings

Achieved 3.7% average F1 improvement across datasets.

Small models with TT-CSW outperform ChatGPT and GPT-4.

Established new benchmarks for cross-lingual ASTE.

Abstract

Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area with impressive outcomes being achieved on high-resource languages. However, the application of cross-lingual transfer to the ASTE task has been relatively unexplored, and current code-switching methods still suffer from term boundary detection issues and out-of-dictionary problems. In this study, we introduce a novel Test-Time Code-SWitching (TT-CSW) framework, which bridges the gap between the bilingual training phase and the monolingual test-time prediction. During training, a generative model is developed based on bilingual code-switched training data and can produce bilingual ASTE triplets for bilingual inputs. In the testing stage, we employ an alignment-based code-switching technique for test-time augmentation. Extensive experiments on cross-lingual ASTE datasets validate the effectiveness of our proposed method. We achieve an average improvement of 3.7% in terms of weighted-averaged F1 in four datasets with different languages. Additionally, we set a benchmark using ChatGPT and GPT-4, and demonstrate that even smaller generative models fine-tuned with our proposed TT-CSW framework surpass ChatGPT and GPT-4 by 14.2% and 5.0% respectively.