论文标题
元学习语义解析的跨语性歧管
Meta-Learning a Cross-lingual Manifold for Semantic Parsing
论文作者
论文摘要
将语义解析器定位以支持新语言需要有效的跨语性概括。最近的工作发现了机器翻译或零击方法的成功，尽管这些方法可能难以模拟母语人士如何提出问题。我们考虑如何有效利用新语言的最小注释示例来进行几次跨语性语义解析。我们引入了一种一阶元学习算法，以在跨语性转移过程中训练具有最大样品效率的语义解析器。我们的算法使用高资源语言来训练解析器，并同时优化低资源语言的跨语性概括。 ATIS上六种语言的结果表明，我们的概括步骤的组合产生了准确的语义解析器，以每种新语言中的源培训数据$ 10％的$ 10％。我们的方法还使用英语对蜘蛛的竞争模型进行训练，并概括了中文，同样，对$ 10％的培训数据进行了采样。
Localizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods although these approaches can struggle to model how native speakers ask questions. We consider how to effectively leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing. We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample efficiency during cross-lingual transfer. Our algorithm uses high-resource languages to train the parser and simultaneously optimizes for cross-lingual generalization for lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling $\le$10% of source training data in each new language. Our approach also trains a competitive model on Spider using English with generalization to Chinese similarly sampling $\le$10% of training data.
