论文标题
形态上意识到单词级翻译
Morphologically Aware Word-Level Translation
论文作者
论文摘要
我们为双语词典诱导提出了一种新型的形态意识概率模型，该模型以结构化的方式共同对词汇翻译和弯曲形态进行建模。我们的模型利用了基本的语言直觉，即词汇是含义的关键词汇单元，而拐点形态提供了其他句法信息。这种方法可带来实质性的改善 - 在监督环境中，6个语言对的准确性平均得分为19％，在弱监督环境中的16％。作为另一个贡献，我们重点介绍了与现代BLI相关的问题，这些问题源于忽略拐点形态，并提出了三个改善任务的建议。
We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information. This approach leads to substantial performance improvements - 19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting. As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task.
