We propose a cross-lingual QG model which uses the following training regime: (i) Unsupervised pretraining of language models in both primary and secondary ...

Jun 6, 2019 · We propose a cross-lingual QG model which uses the following training regime: (i) Unsupervised pretraining of language models in both primary ...

In this paper, we present a cross-lingual model for leveraging a large ques- tion answering dataset in a secondary language. (such as English) to train models ...

Oct 4, 2024 · In this paper, we propose a simple and efficient XLT-QG method that operates without the need for monolingual, parallel, or labeled data in the ...

Apr 16, 2024 · In this paper, we introduce a straightforward and efficient XLT-QG approach that enables the QG model to learn interrogative structures in the ...

Our approach is different from previous work in Cross-lingual Question Answering task in that it only requires English passages to augment the training data, as ...

Configuration Files: config_generator_train_BPE.yaml - Contains the configuration to train the supervised Question generation task.

Oct 6, 2024 · This paper explores a novel approach to cross-lingual transfer for automatic question generation. The key idea is to learn interrogative ...

Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages. Anonymous ACL submission. Abstract.

Oct 7, 2024 · Cross-lingual transfer for QG (XLT-QG) addresses this limitation by allowing models trained on high-resource language datasets to generate ...