شهدت السنوات الأخيرة نجاحا رائعا في نظام الحوار الموجه نحو المهام في نهاية إلى نهج، خاصة عند دمج معلومات المعرفة الخارجية. ومع ذلك، لا تزال جودة الاستجابة المتولدة في معظم النماذج القائمة محدودة، ويرجع ذلك أساسا إلى عدم وجود التفكير الدقيق في المعرفة الحتمية (WRT الرموز المفاهيمية)، مما يجعل من الصعب التقاط التحولات المفهوم وتحديد نية المستخدم الحقيقية في الصليب -task سيناريوهات. لمعالجة هذه المشكلات، نقترح آلية نية جديدة لتحسين معرفة الكيان الحتمي بشكل أفضل. استنادا إلى مثل هذه الآلية، فإننا نقترح أيضا شبكة منطق النية (IR-NET)، والتي تتألف من التفكير المشترك والمتعدد، للحصول على تمثيلات نية من الرموز المفاهيمية التي يمكن استخدامها لالتقاط التحولات المفهوم المتضمنة في المهمة المحادثات المتداولة، بحيث لتحديد نية المستخدم بفعالية وتوليد ردود أكثر دقة. تحقق النتائج التجريبية من فعالية IR-NET، والتي توضح أنها تحقق الأداء الحديثة في مجموعات حوار ملثى متعدد المجالات.
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 to their lack of fine-grained reasoning on deterministic knowledge (w.r.t. conceptual tokens), which makes them difficult to capture the concept shifts and identify user's real intention in cross-task scenarios. To address these issues, we propose a novel intention mechanism to better model deterministic entity knowledge. Based on such a mechanism, we further propose an intention reasoning network (IR-Net), which consists of joint and multi-hop reasoning, to obtain intention-aware representations of conceptual tokens that can be used to capture the concept shifts involved in task-oriented conversations, so as to effectively identify user's intention and generate more accurate responses. Experimental results verify the effectiveness of IR-Net, showing that it achieves the state-of-the-art performance on two representative multi-domain dialog datasets.
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
Abstract Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes' theorem to factorize the dialogue task into two
Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To a
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate transcription. We use the Transformer-based