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:以任务为导向的对话(ToD)代理机构大多限于少数广泛使用的语言,这主要是因为获得每种语言的培训数据的成本高昂。现有的低成本方法依靠跨语言嵌入或天真的机器翻译,在数据效率方面牺牲了大量准确性,在创建可用的对话代理机构方面基本上没有成功。我们建议采用自动方法,用源语言培训数据,用另一种没有培训数据(即零点数)或小型培训(即少点数)的目标语言建立一个高质量运行的对话代理机构。与以往大多数只侧重于对话国跟踪(DST)的跨语言的多语言培训机构相比,我们建立了一个端对端代理。我们表明,我们的方法缩小了数据效率的几发和现有全点方法之间的准确性差距。我们通过(1) 改进对话数据代表,(2) 改进实体觉觉的机器翻译,(3) 自动过滤杂音翻译。我们评价了我们最近双语对话BiToD数据集的处理方法。 在零点设置中,中文对英语的传输,我们建立了端对端点跟踪(D)跟踪(D)跟踪了终端数据率达5 %,我们采用的方法在对话中提高了标准率。