بالنسبة لأنظمة الحوار الموجهة نحو المهام، قم بتدريب وحدة إدارة حوار التعزيز المستندة (RL) تعاني من كفاءة عينة منخفضة وسرعة تقارب بطيئة بسبب المكافآت المتفرعة في RL.لحل هذه المشكلة، اقترح العديد من الاستراتيجيات لإعطاء المكافآت المناسبة عند التدريب RL، لكن مكافآتها تفتقر إلى التفسير ولا يمكنها تقديرها بدقة توزيع أزواج عمل الدولة في الحوار الحقيقية.في هذه الورقة، نقترح نهج نمذجة مكافأة متعددة المستويات يعكس مكافأة في التسلسل الهرمي من ثلاثة مستويات: المجال والفعال والفتحة.بناء على تعلم التعزيز العسكري العكسي، يمكن لنموذج المكافآت المصمم لدينا توفير إشارات مكافأة أكثر دقة وتفسير لأزواج عمل الدولة.تشير التقييمات الواسعة إلى أن نهجنا يمكن تطبيقه على مجموعة واسعة من أنظمة الحوار التعبير في التعلم وتحسن بشكل كبير من كل الأداء وسرعة التقارب.
For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs. In this paper, we propose a multi-level reward modeling approach that factorizes a reward into a three-level hierarchy: domain, act, and slot. Based on inverse adversarial reinforcement learning, our designed reward model can provide more accurate and explainable reward signals for state-action pairs. Extensive evaluations show that our approach can be applied to a wide range of reinforcement learning-based dialog systems and significantly improves both the performance and the speed of convergence.
References used
https://aclanthology.org/
Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited
A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches i
Human conversations naturally evolve around different topics and fluently move between them. In research on dialog systems, the ability to actively and smoothly transition to new topics is often ignored. In this paper we introduce TIAGE, a new topic-
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved. This may result in intent classificati