Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot). Unlike most prior work in cross-lingual ToD that only focuses on Dialogue State Tracking (DST), we build an end-to-end agent. We show that our approach closes the accuracy gap between few-shot and existing full-shot methods for ToD agents. We achieve this by (1) improving the dialogue data representation, (2) improving entity-aware machine translation, and (3) automatic filtering of noisy translations. We evaluate our approach on the recent bilingual dialogue dataset BiToD. In Chinese to English transfer, in the zero-shot setting, our method achieves 46.7% and 22.0% in Task Success Rate (TSR) and Dialogue Success Rate (DSR) respectively. In the few-shot setting where 10% of the data in the target language is used, we improve the state-of-the-art by 15.2% and 14.0%, coming within 5% of full-shot training.

翻译：任务型对话（ToD）代理主要局限于少数广泛使用的语言，这主要是因为获取每种语言训练数据的高昂成本。现有依赖跨语言嵌入或简单机器翻译的低成本方法在数据效率上牺牲了大量准确性，并且大多无法构建可用的对话代理。我们提出了一种自动化方法，利用源语言的ToD训练数据，在目标语言中构建高质量的功能性对话代理，该目标语言没有训练数据（即零样本）或仅有少量训练集（即少样本）。与大多数仅关注对话状态跟踪（DST）的跨语言ToD先前工作不同，我们构建了一个端到端代理。我们证明，我们的方法缩小了ToD代理在少样本与现有全样本方法之间的准确性差距。我们通过以下方式实现这一目标：（1）改进对话数据表示，（2）改进实体感知的机器翻译，以及（3）自动过滤噪声翻译。我们在最近的双语对话数据集BiToD上评估了我们的方法。在从中文到英文的迁移中，在零样本设置下，我们的方法在任务成功率（TSR）和对话成功率（DSR）上分别达到46.7%和22.0%。在少样本设置下（使用目标语言中10%的数据），我们将最先进水平提升了15.2%和14.0%，使结果接近全样本训练的5%以内。