Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition
إطار تعلم التعزيز متعدد الوكلات التعاونية لتحليل إجراء الحوار
243
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقوم معظم طرق التعلم في مجال التعزيز لسياسة الحوار، قم بتدريب تعلم وكيل مركزي يختار إجراء مشترك محدد مسبقا اسم النطاق ونوع النية واسم الفتحة. يعاني وكيل الحوار المركزي من متطلبات العديد من متطلبات تفاعل المستخدمين لعمل المستخدمين بسبب مساحة العمل الكبيرة. إضافة إلى ذلك، فإن تصميم الإجراءات المتسلسلة شاقة للمهندسين وربما كافح مع حالات الحافة. لحل هذه المشاكل، نقوم بنمط مشكلة تعلم سياسة الحوار مع إطار جديد متعدد الوكلاء، حيث يقود كل جزء من الإجراء من قبل وكيل مختلف. الإطار يقلل من تكاليف العمل لقوالب الإجراءات ويقلل من حجم مساحة العمل لكل وكيل. علاوة على ذلك، نقوم بتخفيف المشكلة غير الثابتة الناجمة عن ديناميات البيئة المتغيرة كتطور سياسات الوكلاء من خلال إدخال عملية تحسين مشتركة تجعل الوكلاء يمكنهم تبادل معلومات سياستهم. في الوقت نفسه، يتم دمج آلية إعادة تشغيل تجربة مخزنة مستقلة لتقليل الاعتماد بين تدرجات العينات لتحسين كفاءة التدريب. يتم إثبات فعالية الإطار المقترح في بيئة متعددة المجالات مع كل من تقييم محاكي المستخدم والتقييم البشري.
Most reinforcement learning methods for dialog policy learning train a centralized agent that selects a predefined joint action concatenating domain name, intent type, and slot name. The centralized dialog agent suffers from a great many user-agent interaction requirements due to the large action space. Besides, designing the concatenated actions is laborious to engineers and maybe struggled with edge cases. To solve these problems, we model the dialog policy learning problem with a novel multi-agent framework, in which each part of the action is led by a different agent. The framework reduces labor costs for action templates and decreases the size of the action space for each agent. Furthermore, we relieve the non-stationary problem caused by the changing dynamics of the environment as evolving of agents' policies by introducing a joint optimization process that makes agents can exchange their policy information. Concurrently, an independent experience replay buffer mechanism is integrated to reduce the dependence between gradients of samples to improve training efficiency. The effectiveness of the proposed framework is demonstrated in a multi-domain environment with both user simulator evaluation and human evaluation.
References used
https://aclanthology.org/
rate research
Read More
Large-scale multi-modal classification aim to distinguish between different multi-modal data, and it has drawn dramatically attentions since last decade. In this paper, we propose a multi-task learning-based framework for the multimodal classificatio
n task, which consists of two branches: multi-modal autoencoder branch and attention-based multi-modal modeling branch. Multi-modal autoencoder can receive multi-modal features and obtain the interactive information which called multi-modal encoder feature, and use this feature to reconstitute all the input data. Besides, multi-modal encoder feature can be used to enrich the raw dataset, and improve the performance of downstream tasks (such as classification task). As for attention-based multimodal modeling branch, we first employ attention mechanism to make the model focused on important features, then we use the multi-modal encoder feature to enrich the input information, achieve a better performance. We conduct extensive experiments on different dataset, the results demonstrate the effectiveness of proposed framework.
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
mount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.
To date, most abstractive summarisation models have relied on variants of the negative log-likelihood (NLL) as their training objective. In some cases, reinforcement learning has been added to train the models with an objective that is closer to thei
r evaluation measures (e.g. ROUGE). However, the reward function to be used within the reinforcement learning approach can play a key role for performance and is still partially unexplored. For this reason, in this paper, we propose two reward functions for the task of abstractive summarisation: the first function, referred to as RwB-Hinge, dynamically selects the samples for the gradient update. The second function, nicknamed RISK, leverages a small pool of strong candidates to inform the reward. In the experiments, we probe the proposed approach by fine-tuning an NLL pre-trained model over nine summarisation datasets of diverse size and nature. The experimental results show a consistent improvement over the negative log-likelihood baselines.
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models
usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.
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
mproved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.
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
