论文标题
udapter：真正普遍依赖解析的语言适应
UDapter: Language Adaptation for Truly Universal Dependency Parsing
论文作者
论文摘要
多语言依赖解析的最新进展使一个真正的普遍解析器更接近现实的想法。但是，跨语言干扰和约束模型容量仍然是主要障碍。为了解决这个问题，我们根据上下文参数生成和适配器模块提出了一种新型的多语言任务适应方法。这种方法使能够通过语言嵌入学习适配器，同时跨语言共享模型参数。它还允许将现有语言类型学特征的简便但有效整合到解析网络中。最终的解析器，UDAPTER在大多数高资源和低资源（零射）语言上都优于强大的单语和多语言基线，显示了拟议适应方法的成功。我们的深入分析表明，通过类型学特征进行软参数共享是这一成功的关键。
Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a novel multilingual task adaptation approach based on contextual parameter generation and adapter modules. This approach enables to learn adapters via language embeddings while sharing model parameters across languages. It also allows for an easy but effective integration of existing linguistic typology features into the parsing network. The resulting parser, UDapter, outperforms strong monolingual and multilingual baselines on the majority of both high-resource and low-resource (zero-shot) languages, showing the success of the proposed adaptation approach. Our in-depth analyses show that soft parameter sharing via typological features is key to this success.
