Evaluating and explaining training strategies for zero-shot cross-lingual news sentiment analysis
This work addresses the problem of building robust sentiment classifiers for multiple languages without target-language data, which is incremental as it builds on existing cross-lingual methods with new datasets and approaches.
The paper tackled zero-shot cross-lingual news sentiment analysis by evaluating strategies like machine translation, in-context learning, and a novel POA objective, achieving significant improvements over state-of-the-art methods, with in-context learning performing best and POA offering a competitive alternative with lower computational cost.
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.