يعد عدم وجود بيانات تدريبية المسمى للميزات الجديدة مشكلة شائعة في أنظمة الحوار في العالم الحقيقي المتغيرة بسرعة.كحل، نقترح نموذج توليد إعادة صياغة متعددة اللغات يمكن استخدامه لإنشاء كلمات جديدة للميزة المستهدفة واللغة المستهدفة.يمكن استخدام الكلام الذي تم إنشاؤه لزيادة بيانات التدريب الحالية لتحسين تصنيف نماذج وضع العلامات الفضائية.نحن نقيم جودة الكلام التي تم إنشاؤها باستخدام مقاييس التقييم الجوهرية وإجراء تجارب التقييم المصب مع اللغة الإنجليزية كلغة مصدر وتسع لغات مستهدفة مختلفة.تعرض طريقنا وعد عبر اللغات، حتى في إعداد طلقة صفرية حيث لا توجد بيانات بذرة متاحة.
The lack of labeled training data for new features is a common problem in rapidly changing real-world dialog systems. As a solution, we propose a multilingual paraphrase generation model that can be used to generate novel utterances for a target feature and target language. The generated utterances can be used to augment existing training data to improve intent classification and slot labeling models. We evaluate the quality of generated utterances using intrinsic evaluation metrics and by conducting downstream evaluation experiments with English as the source language and nine different target languages. Our method shows promise across languages, even in a zero-shot setting where no seed data is available.
References used
https://aclanthology.org/
As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promis
Generative models for dialog systems have gained much interest because of the recent success of RNN and Transformer based models in tasks like question answering and summarization. Although the task of dialog response generation is generally seen as
Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user
Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to