Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations

arXiv:2404.02452v1 Announce Type: new
Abstract: Zero-Shot Cross-lingual Transfer (ZS-XLT) utilizes a model trained in a source language to make predictions in another language, often with a performance loss. To alleviate this, additional improvements can be achieved through subsequent adaptation using examples in the target language. In this paper, we exploit In-Context Tuning (ICT) for One-Shot Cross-lingual transfer in the classification task by introducing In-Context Cross-lingual Transfer (IC-XLT). The novel concept involves training a model to learn from context examples and …

abstract arxiv classification context cross-lingual cs.cl examples exploit improvements language loss paper performance predictions text text classification through transfer type zero-shot