ixa-ehu/ixambert-base-cased

The model has been successfully used to transfer knowledge from English to Basque in a conversational QA system . The training corpora is composed by the English, Spanish and Basque Wikipedias, together with Basque crawled news articles from online newspapers . In the Transfer Learning setting the model is first fine-tuned on QuaC, an English CQA dataset, and then on a Basque dataset . If using this model, please cite the publication of the paper Conversational Question Answering in Low Resource Scenarios: A Dataset and Case Study for Basque, as shown in the following Table: XIXAmBERT performed better than mBERT when,