论文标题
CrossAligner＆Co：用于任务跨语言自然语言理解的零射击转移方法
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding
论文作者
论文摘要
面向任务的个人助理使人们能够使用自然语言与许多设备和服务进行互动。使更多用户可以使用神经对话系统的挑战之一是除几种语言以外的所有语言都缺乏培训数据。零击方法试图通过以高资源语言（例如英语）获取任务知识来解决此问题，目的是将其转移到低资源语言中。为此，我们介绍了CrossAligner，这是基于未标记并联数据的学习对齐方式进行零击的多种有效方法的主要方法。我们提供了对单个方法及其加权组合的定量分析，其中一些超过了跨九种语言，十五个测试集和3个基准测试的多语言数据集的最新分数（SOTA）分数。对最佳方法的详细定性错误分析表明，我们的微调语言模型可以零弹性地传输任务知识比预期的更好。
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems available to more users is the lack of training data for all but a few languages. Zero-shot methods try to solve this issue by acquiring task knowledge in a high-resource language such as English with the aim of transferring it to the low-resource language(s). To this end, we introduce CrossAligner, the principal method of a variety of effective approaches for zero-shot cross-lingual transfer based on learning alignment from unlabelled parallel data. We present a quantitative analysis of individual methods as well as their weighted combinations, several of which exceed state-of-the-art (SOTA) scores as evaluated across nine languages, fifteen test sets and three benchmark multilingual datasets. A detailed qualitative error analysis of the best methods shows that our fine-tuned language models can zero-shot transfer the task knowledge better than anticipated.
