جعلت نموذج الاستفادة من النماذج اللغوية الكبيرة المدربة مسبقا تقدما ملحوظا على معايير نظم الحوار الموجهة نحو المهام (TOD).في هذه الورقة، نجمع بين هذه النموذج مع إطار تعليمي متعدد المهام لنمذجة TOD نهاية إلى الطرفية من خلال اعتماد التنبؤ SPAN كامرأة مساعدة.في الإعداد المحرز، يحقق نموذجنا نتائج أحدث نتائج جديدة مع درجات مشتركة من 108.3 و 107.5 على MultiWoz 2.0 و MultiWoz 2.1، على التوالي.علاوة على ذلك، نوضح أن التعلم متعدد المهام يحسن ليس فقط أداء النموذج ولكن قدرة تعميمه من خلال تجارب تكيف المجال في إعداد القليل من اللقطة.الرمز متاح في github.com/bepoetree/mttod.
The paradigm of leveraging large pre-trained language models has made significant progress on benchmarks on task-oriented dialogue (TOD) systems. In this paper, we combine this paradigm with multi-task learning framework for end-to-end TOD modeling by adopting span prediction as an auxiliary task. In end-to-end setting, our model achieves new state-of-the-art results with combined scores of 108.3 and 107.5 on MultiWOZ 2.0 and MultiWOZ 2.1, respectively. Furthermore, we demonstrate that multi-task learning improves not only the performance of model but its generalization capability through domain adaptation experiments in the few-shot setting. The code is available at github.com/bepoetree/MTTOD.
References used
https://aclanthology.org/
Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context. The existing works represent the
We propose a novel problem within end-to-end learning of task oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain
For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small a
Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. However, the quality of most existing models' generated response is still limited, mainly due t
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