MetaXCR: Reinforcement-Based Meta-Transfer Learning for Cross-Lingual Commonsense Reasoning
This addresses the problem of costly annotation and data scarcity in non-English commonsense reasoning for NLP researchers, though it is incremental as it builds on existing meta-learning and cross-lingual techniques.
The paper tackles cross-lingual commonsense reasoning with limited labeled data by proposing MetaXCR, a framework that uses meta-learning with multiple datasets and reinforcement-based sampling to adapt to new languages, achieving superior performance over state-of-the-art methods while using fewer parameters.
Commonsense reasoning (CR) has been studied in many pieces of domain and has achieved great progress with the aid of large datasets. Unfortunately, most existing CR datasets are built in English, so most previous work focus on English. Furthermore, as the annotation of commonsense reasoning is costly, it is impossible to build a large dataset for every novel task. Therefore, there are growing appeals for Cross-lingual Low-Resource Commonsense Reasoning, which aims to leverage diverse existed English datasets to help the model adapt to new cross-lingual target datasets with limited labeled data. In this paper, we propose a multi-source adapter for cross-lingual low-resource Commonsense Reasoning (MetaXCR). In this framework, we first extend meta learning by incorporating multiple training datasets to learn a generalized task adapters across different tasks. Then, we further introduce a reinforcement-based sampling strategy to help the model sample the source task that is the most helpful to the target task. Finally, we introduce two types of cross-lingual meta-adaption methods to enhance the performance of models on target languages. Extensive experiments demonstrate MetaXCR is superior over state-of-the-arts, while being trained with fewer parameters than other work.