论文标题
引导跨语言语义解析器
Bootstrapping a Crosslingual Semantic Parser
论文作者
论文摘要
语义解析的最新进展几乎不考虑英语以外的其他语言，但专业翻译的态度可能非常昂贵。我们将接受单一语言训练的语义解析器（例如英语）调整为新的语言和多个域，并具有最小的注释。我们查询机器翻译是否可以替代培训数据，并将其扩展到使用英语，释义和多语言的预训练模型的联合培训来调查引导。我们通过将注意力集中在多个编码器上，并在德语和中文中呈现新版本的ATIS和隔夜进行评估，从而开发了一个基于变压器的解析器，从而结合了释义。实验结果表明，MT可以在新语言中近似培训数据，以通过通过多个MT发动机进行释义时进行准确解析。考虑到MT何时不足，我们还发现，使用我们的方法仅使用50％的培训数据来实现完全翻译的2％以内的解析精度。
Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and multiple domains with minimal annotation. We query if machine translation is an adequate substitute for training data, and extend this to investigate bootstrapping using joint training with English, paraphrasing, and multilingual pre-trained models. We develop a Transformer-based parser combining paraphrases by ensembling attention over multiple encoders and present new versions of ATIS and Overnight in German and Chinese for evaluation. Experimental results indicate that MT can approximate training data in a new language for accurate parsing when augmented with paraphrasing through multiple MT engines. Considering when MT is inadequate, we also find that using our approach achieves parsing accuracy within 2% of complete translation using only 50% of training data.
