# Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis

arXiv: https://arxiv.org/abs/2409.20054 · HTML: https://mlsanity.com/paper/2409.20054/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 58 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [On Limitations of the Transformer Architecture](https://mlsanity.com/paper/2402.08164/) (2024)
- [Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing](https://mlsanity.com/paper/1909.06775/) (2019)
- [Multinomial Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/1802.05694/) (2018)
- [SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics](https://mlsanity.com/paper/2005.04114/) (2020)
- [Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1909.00437/) (2019)
- [Sentiment Analysis in the News](https://mlsanity.com/paper/1309.6202/) (2013)
- [Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model](https://mlsanity.com/paper/1909.09587/) (2019)
- [Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure](https://mlsanity.com/paper/2203.08430/) (2022)
- [Explicit Cross-lingual Pre-training for Unsupervised Machine Translation](https://mlsanity.com/paper/1909.00180/) (2019)
- [Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens](https://mlsanity.com/paper/1805.02214/) (2018)
- [T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification](https://mlsanity.com/paper/2306.04996/) (2023)
- [Cross-Lingual Sentiment Analysis Without (Good) Translation](https://mlsanity.com/paper/1707.01626/) (2017)
- [Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised?](https://mlsanity.com/paper/2202.06650/) (2022)
- [AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining](https://mlsanity.com/paper/2312.15784/) (2023)

## Built on by (most cited first, 1 of 1)

- [Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation](https://mlsanity.com/paper/2507.11634/) (2025)

## Abstract (arXiv)

We investigate zero-shot cross-lingual news sentiment detection, aiming to develop robust sentiment classifiers that can be deployed across multiple languages without target-language training data. We introduce novel evaluation datasets in several less-resourced languages, and experiment with a range of approaches including the use of machine translation; in-context learning with large language models; and various intermediate training regimes including a novel task objective, POA, that leverages paragraph-level information. Our results demonstrate significant improvements over the state of the art, with in-context learning generally giving the best performance, but with the novel POA approach giving a competitive alternative with much lower computational overhead. We also show that language similarity is not in itself sufficient for predicting the success of cross-lingual transfer, but that similarity in semantic content and structure can be equally important.