Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDomain-independent User Simulation with Transformers for Task-oriented Dialogue Systems
محاكاة المستخدم المستقلة للنطاق مع محولات أنظمة الحوار الموجهة نحو المهام
577
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتطلب تحسين سياسة الحوار عبر التعلم التعزيز عددا كبيرا من التفاعلات التدريبية، مما يجعل التعلم مع المستخدمين الحقيقيين الوقت المستهلكة ومكلفة. لذلك يعتمد العديد من الإعدادات على محاكاة المستخدم بدلا من البشر. لدى محاكاة المستخدم هذه مشاكلهم الخاصة. في حين أن محاكاة المستخدمين المشفرة باليد، فقد ثبت أن محاكاة المستخدمين الذين يعتمدون على القواعد كافية في المجالات الصغيرة والبسيطة، لأن عدد القواعد المعقدة بسرعة أصلي. لا تزال محاكاة المستخدم التي يحركها بيانات البيانات، من ناحية أخرى، تعتمد على المجال. هذا يعني أن التكيف مع كل مجال جديد يتطلب إعادة تصميم وإعادة التدريب. في هذا العمل، نقترح محاكاة للمستخدم المستقل المستقل للمجال (TUS). لا يتم ربط هيكل TUS مجال معين، وتمكين تعميم المجال وتعلم سلوك المستخدم عبر المجال من البيانات. نحن نقارن TUS مع أحدث التقيمات التلقائية وكذلك الإنسان. يمكن أن يتنافس TUS مع محاكاة المستخدمين المستند إلى القواعد على المجالات المحددة مسبقا ويمكن أن يعممون إلى المجالات غير المرئية في أزياء صفرية.
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 simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.
References used
https://aclanthology.org/
rate research
Read More
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
frequent changes, and initial training dialogues may soon become obsolete, resulting in a significant decrease in the model performance. In this paper, we investigate the relationship between training dialogues and domain knowledge, and propose Dialogue Domain Adaptation, a methodology aiming at adapting initial training dialogues to changes intervened in the domain knowledge. We focus on slot-value changes (e.g., when new slot values are available to describe domain entities) and define an experimental setting for dialogue domain adaptation. First, we show that current state-of-the-art models for dialogue state tracking are still poorly robust to slot-value changes of the domain knowledge. Then, we compare different domain adaptation strategies, showing that simple techniques are effective to reduce the gap between training dialogues and domain knowledge.
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot fillin
g and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.
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
continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in both modularized and end-to-end learning settings. In addition, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. We also suggest that the upper bound performance of continual learning should be equivalent to multitask learning when data from all domain is available at once. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform better, by a large margin, compared to other continuous learning techniques, and only slightly worse than the multitask learning upper bound while being 20X faster in learning new domains. We also report several trade-offs in terms of parameter usage, memory size and training time, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released to promote more research in this direction.
This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems. We introduce the task, the main datasets that have been exploited as well as their evaluation metr
ics, and we analyze several proposed approaches. We distinguish between static ontology DST models, which predict a fixed set of dialogue states, and dynamic ontology models, which can predict dialogue states even when the ontology changes. We also discuss the model's ability to track either single or multiple domains and to scale to new domains, both in terms of knowledge transfer and zero-shot learning. We cover a period from 2013 to 2020, showing a significant increase of multiple domain methods, most of them utilizing pre-trained language models.
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
entity with only perceiving a part of its KB context, which can lead to the less effective representation due to the information loss, and adversely favor KB reasoning and response generation. To tackle this issue, we explore to fully contextualize the entity representation by dynamically perceiving all the relevant entities and dialogue history. To achieve this, we propose a COntext-aware Memory Enhanced Transformer framework (COMET), which treats the KB as a sequence and leverages a novel Memory Mask to enforce the entity to only focus on its relevant entities and dialogue history, while avoiding the distraction from the irrelevant entities. Through extensive experiments, we show that our COMET framework can achieve superior performance over the state of the arts.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
