Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.
The Hong Kong University of Science and Technology（香港科技大学）
It is difficult to train a personalized task-oriented dialogue system because the data collected from each individual is often insufficient. Personalized dialogue systems trained on a small dataset can overfit and make it difficult to adapt to different user needs. One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain. By following this idea, we propose "PETAL"(PErsonalized Task-oriented diALogue), a transfer-learning framework…
Hong Kong University of Science and Technology（香港科技大学）
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient. One common practice for this problem is to share training dialogues between different users and train multiple sequence-to-sequence dialogue models together with transfer learning. However, current sequence-to-sequence transfer learning models operate on the entire sentence, which might cause negative transfer if different personal information from different users is mixed up. We propose a personalized decoder model to transfer finer granularity phrase-level knowled…
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive set…
Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for modelling such dialogues. In this paper, we focus on the under-explored problem of multi-domain dialogue management. First, we propose a new method for hierarchical reinforcement learning using the option framework. Next, we show that the proposed architecture learns faster and arrives at a better policy than the existing flat ones do. Moreover, we show how…
An Embodied Conversational Agent (ECA) is an intelligent agent that works as the front end of software applications to interact with users through verbal/nonverbal expressions and to provide online assistance without the limits of time, location, and language. To help to improve the experience of human-computer interaction, there is an increasing need to empower ECA with not only the realistic look of its human counterparts but also a higher level of intelligence. This thesis first highlights the main topics related to the construction of ECA, including different approaches of dialogue managem…
University of Cambridge（剑桥大学）；PolyAI Limited（PolyAI有限公司）
Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation. Traditional RL algorithms, however, fail to scale to large domains due to the curse of dimensionality. We propose a novel Dialogue Management architecture, based on Feudal RL, which decomposes the decision into two steps; a first step where a master policy selects a subset of primitive actions, and a second step where a primitive action is chosen from the selected subset. The structural information included in the domain ontology is used to abstract the dialogue state space, taking the decisions at each …
Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with real users. Two approaches are introduced to tackle this problem. Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented. For TRACER, the trust region helps to control the learning step si…
Shanghai Jiao Tong University（上海交通大学）；Heinrich Heine University Düsseldorf（海因里希·海涅大学（杜塞尔多夫））
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: 1) Many DRL-based policies are not sample-efficient. 2) Most models don't have the capability of policy transfer between different domains. In this paper, we propose a universal framework, AgentGraph, to tackle these two problems. The proposed AgentGraph is the combination of GNN-based architecture and DR…
Sparebank 1 SR-Bank；Center for Artificial Intelligence Research（人工智能研究中心）；University of Agder（阿格德大学）
The common purpose of applying reinforcement learning (RL) to asset management is the maximization of profit. The extrinsic reward function used to learn an optimal strategy typically does not take into account any other preferences or constraints. We have developed a regularization method that ensures that strategies have global intrinsic affinities, i.e., different personalities may have preferences for certain assets which may change over time. We capitalize on these intrinsic policy affinities to make our RL model inherently interpretable. We demonstrate how RL agents can be trained to orc…
In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning methods are very promising but rely on epsilon-greedy exploration, thus subjecting the user to a random choice of action during learning. Alternative approaches such as Gaussian Process SARSA (GPSARSA) estimate uncertainties and are sample efficient, leading to better user experience, but on the expense of a greater computational complexity. This paper examine…
Northeastern University（东北大学）；University of Maryland（马里兰大学）；New York University School of Medicine（纽约大学医学院）；NYU Langone Health（纽约大学朗格尼健康中心）
Comorbid chronic conditions are common among people with type 2 diabetes. We developed an Artificial Intelligence algorithm, based on Reinforcement Learning (RL), for personalized diabetes and multi-morbidity management with strong potential to improve health outcomes relative to current clinical practice. In this paper, we modeled glycemia, blood pressure and cardiovascular disease (CVD) risk as health outcomes using a retrospective cohort of 16,665 patients with type 2 diabetes from New York University Langone Health ambulatory care electronic health records in 2009 to 2017. We trained a RL …
Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希·海涅大学）；University of Cambridge（剑桥大学）
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL). Optimisation via RL is highly susceptible to sample inefficiency and instability. The hierarchical approach called Feudal Dialogue Management takes a step towards more efficient learning by decomposing the action space. However, it still suffers from instability due to the reward only being provided at the end of the dialogue. We propose the usage of an intrinsic reward based on information gain to address this issue. Our proposed reward favours actions that resolve unce…
Tsinghua University（清华大学）；Samsung Research China - Beijing (SRC-B)（三星中国研究院-北京（SRC-B））；NetEase Inc.（网易公司）
Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the persona sparsity issue observed in most dialogue corpora. This paper proposes a pre-training based personalized dialogue model that can generate coherent responses using persona-sparse dialogue data. In this method, a pre-trained language model is used to initialize an encoder and decoder, and personal attribute embeddings are devised to model richer dialogue cont…
Our project task was to create a model that, given a speaker ID, chat history, and an utterance query, can predict the response utterance in a conversation. The model is personalized for each speaker. This task can be a useful tool for building speech bots that talk in a human-like manner in a live conversation. Further, we succeeded at using dense-vector encoding clustering to be able to retrieve relevant historical dialogue context, a useful strategy for overcoming the input limitations of neural-based models when predictions require longer-term references from the dialogue history. In this …
Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models tend to be self-centered, with little care for the user in the dialogue. Moreover, we consider that human-like conversation is essentially built based on inferring information about the persona of the other party. Motivated by this, we propose a novel personalized dialogue generator by detecting an implicit user persona. Because it is hard to collect a larg…
Renmin University of China（中国人民大学）；University of Montreal（蒙特利尔大学）
Personalized chatbots focus on endowing the chatbots with a consistent personality to behave like real users and further act as personal assistants. Previous studies have explored generating implicit user profiles from the user's dialogue history for building personalized chatbots. However, these studies only use the response generation loss to train the entire model, thus it is prone to suffer from the problem of data sparsity. Besides, they overemphasize the final generated response's quality while ignoring the correlations and fusions between the user's dialogue history, leading to rough da…
We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software. Their purpose is to make machine-learning based dialogue management and language understanding accessible to non-specialist software developers. In terms of design philosophy, we aim for ease of use, and bootstrapping from minimal (or no) initial training data. Both packages are extensively documented and ship with a comprehensive suite of tests. The code is available at https://github.com/RasaHQ/
Melanoma is the most lethal type of skin cancer. Patients are vulnerable to mental health illnesses which can reduce the effectiveness of the cancer treatment and the patients adherence to drug plans. It is crucial to preserve the mental health of patients while they are receiving treatment. However, current art therapy approaches are not personal and unique to the patient. We aim to provide a well-trained image style transfer model that can quickly generate unique art from personal dermoscopic melanoma images as an additional tool for art therapy in disease management of melanoma. Visual art …
Personalized Weight Loss Management through Wearable Devices and Artificial Intelligence
Department of Mathematics, Universidad de Las Palmas de Gran Canaria, 35001, Spain（拉斯帕尔马斯德Gran Canaria大学数学系）；Cancer Research Program, IMDEA Food Institute（IMDEA食品研究所癌症研究计划）；Health, IMDEA Food Institute（IMDEA食品研究所健康）
