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

arXiv: https://arxiv.org/abs/2501.14144 · HTML: https://mlsanity.com/paper/2501.14144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog](https://mlsanity.com/paper/1810.13327/) (2018)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [A Unified Generative Framework for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2106.04300/) (2021)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP](https://mlsanity.com/paper/2006.06402/) (2020)
- [Zero-Shot Cross-Lingual Transfer with Meta Learning](https://mlsanity.com/paper/2003.02739/) (2020)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus](https://mlsanity.com/paper/2004.06295/) (2020)
- [Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2103.07665/) (2021)
- [Frustratingly Easy Label Projection for Cross-lingual Transfer](https://mlsanity.com/paper/2211.15613/) (2022)
- [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021)
- [A Fine-Grained Sentiment Dataset for Norwegian](https://mlsanity.com/paper/1911.12722/) (2019)
- [Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training](https://mlsanity.com/paper/2104.08645/) (2021)
- [MultiBooked: A Corpus of Basque and Catalan Hotel Reviews Annotated for Aspect-level Sentiment Classification](https://mlsanity.com/paper/1803.08614/) (2018)
- [Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation](https://mlsanity.com/paper/2010.14271/) (2020)

## Abstract (arXiv)

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.