Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContinual Learning in Task-Oriented Dialogue Systems
التعلم المستمر في نظم الحوار الموجهة نحو المهام
383
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يسمح التعلم المستمر في أنظمة الحوار الموجهة نحو المهام للنظام بإضافة مجالات ووظائف جديدة للعمل الإضافي بعد النشر، دون تكبد التكلفة العالية لإعادة النظر في النظام بأكمله في كل مرة. في هذه الورقة، نقترح أول معيار تعلم مستمر على الإطلاق لأنظمة الحوار الموجهة نحو المهام مع أن يتم تعلم 37 نطما بشكل مستمر في إعدادات التعلم المعدلة والنهاية. بالإضافة إلى ذلك، نقوم بتنفيذ ومقارنة خطوط أساسيات التعلم المستمرة المتعددة، ونقترحنا طريقة معمارية بسيطة ولكنها فعالة تعتمد على المحولات المتبقية. نشير أيضا إلى أن الأداء العلوي للتعلم المستمر يجب أن يكون يعادل التعلم المتعدد المهام عند توفر البيانات من جميع المجال في وقت واحد. توضح تجاربنا أن الطريقة المعمارية المقترحة وإجراءات استراتيجية تستند إلى إعادة التشغيل بسيطة تؤدي بشكل أفضل، من خلال هامش كبير، مقارنة بتقنيات التعلم المستمرة الأخرى، وأسوأ قليلا قليلا من العلوي المتعدد التعلم العلوي أثناء كونه 20x بشكل أسرع في تعلم النطاقات الجديدة. نحن نبلغ أيضا العديد من المفاضلات من حيث استخدام المعلمة وحجم الذاكرة ووقت التدريب، وهي مهمة في تصميم نظام حوار موجه نحو المهام. يتم إصدار المعيار المقترح لتعزيز المزيد من البحث في هذا الاتجاه.
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.
References used
https://aclanthology.org/
rate research
Read More
Abstract Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses. Existing approaches require dialog datasets to explicitly annotat
e these KB queries---these annotations can be time consuming, and expensive. In response, we define the novel problems of predicting the KB query and training the dialog agent, without explicit KB query annotation. For query prediction, we propose a reinforcement learning (RL) baseline, which rewards the generation of those queries whose KB results cover the entities mentioned in subsequent dialog. Further analysis reveals that correlation among query attributes in KB can significantly confuse memory augmented policy optimization (MAPO), an existing state of the art RL agent. To address this, we improve the MAPO baseline with simple but important modifications suited to our task. To train the full TOD system for our setting, we propose a pipelined approach: it independently predicts when to make a KB query (query position predictor), then predicts a KB query at the predicted position (query predictor), and uses the results of predicted query in subsequent dialog (next response predictor). Overall, our work proposes first solutions to our novel problem, and our analysis highlights the research challenges in training TOD systems without query annotation.
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.
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.
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.
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.
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
