Question answering is one of the most challenging tasks in language understanding. Most approaches are developed for English, while less-resourced languages are much less researched. We adapt a successful English question-answering approach, called UnifiedQA, to the less-resourced Slovene language. Our adaptation uses the encoder-decoder transformer SloT5 and mT5 models to handle four question-answering formats: yes/no, multiple-choice, abstractive, and extractive. We use existing Slovene adaptations of four datasets, and machine translate the MCTest dataset. We show that a general model can answer questions in different formats at least as well as specialized models. The results are further improved using cross-lingual transfer from English. While we produce state-of-the-art results for Slovene, the performance still lags behind English.
翻译:问题解答是语言理解方面最具挑战性的任务之一。 大多数方法是为英语开发的,而资源较少的语言则少得多。 我们将成功的英语问答方法,叫做统一QA, 改用资源较少的斯洛文尼亚语。 我们的适应用编码器-解码器变压器 SloT5 和 mT5 模型处理四种答答格式:是/否、多选取、抽象和采掘。 我们使用斯洛文尼亚语现有四个数据集的调整,机器翻译MCTest数据集。 我们显示,通用模型至少可以不同格式和专业模型回答问题。 使用英语的跨语言传输,其结果会进一步改进。 我们为斯洛文尼亚语制作了最新的结果,但表现仍然落后于英语。