Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based mental health conversations could improve access to treatment and reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, the ability to understand and feel the emotions and experiences of others, is a key component leading to positive outcomes in supportive conversations. However, recent studies have shown that highly empathic conversations are rare in online mental health platforms. In this paper, we work towards improving empathy in online mental health support conversations. We introduce a new task of empathic rewriting which aims to transform low-empathy conversational posts to higher empathy. Learning such transformations is challenging and requires a deep understanding of empathy while maintaining conversation quality through text fluency and specificity to the conversational context. Here we propose PARTNER, a deep reinforcement learning agent that learns to make sentence-level edits to posts in order to increase the expressed level of empathy while maintaining conversation quality. Our RL agent leverages a policy network, based on a transformer language model adapted from GPT-2, which performs the dual task of generating candidate empathic sentences and adding those sentences at appropriate positions. During training, we reward transformations that increase empathy in posts while maintaining text fluency, context specificity and diversity. Through a combination of automatic and human evaluation, we demonstrate that PARTNER successfully generates more empathic, specific, and diverse responses and outperforms NLP methods from related tasks like style transfer and empathic dialogue generation. Our work has direct implications for facilitating empathic conversations on web-based platforms.
相關內容
Replacing a fossil fuel-powered car with an electric model can halve greenhouse gas emissions over the course of the vehicle's lifetime and reduce the noise pollution in urban areas. In green logistics, a well-scheduled charging ensures an efficient operation of transportation and power systems and, at the same time, provides economical and satisfactory charging services for drivers. This paper presents a taxonomy of current electric vehicle charging scheduling problems in green logistics by analyzing its unique features with some typical use cases, such as space assignment, routing and energy management; discusses the challenges, i.e., the information availability and stakeholders' strategic behaviors that arise in stochastic and decentralized environments; and classifies the existing approaches, as centralized, distributed and decentralized ones, that apply to these challenges. Moreover, we discuss research opportunities in applying market-based mechanisms, which shall be coordinated with stochastic optimization and machine learning, to the decentralized, dynamic and data-driven charging scheduling problems for the management of the future green logistics.
Conversations on social media (SM) are increasingly being used to investigate social issues on the web, such as online harassment and rumor spread. For such issues, a common thread of research uses adversarial reactions, e.g., replies pointing out factual inaccuracies in rumors. Though adversarial reactions are prevalent in online conversations, inferring those adverse views (or stance) from the text in replies is difficult and requires complex natural language processing (NLP) models. Moreover, conventional NLP models for stance mining need labeled data for supervised learning. Getting labeled conversations can itself be challenging as conversations can be on any topic, and topics change over time. These challenges make learning the stance a difficult NLP problem. In this research, we first create a new stance dataset comprised of three different topics by labeling both users' opinions on the topics (as in pro/con) and users' stance while replying to others' posts (as in favor/oppose). As we find limitations with supervised approaches, we propose a weakly-supervised approach to predict the stance in Twitter replies. Our novel method allows using a smaller number of hashtags to generate weak labels for Twitter replies. Compared to supervised learning, our method improves the mean F1-macro by 8\% on the hand-labeled dataset without using any hand-labeled examples in the training set. We further show the applicability of our proposed method on COVID 19 related conversations on Twitter.
Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems is the partially observable cooperative multiagent setting, in which a team of agents learns to coordinate their behaviors conditioning on their private observations and commonly shared global reward signals. One natural solution is to resort to the centralized training and decentralized execution paradigm. During centralized training, one key challenge is the multiagent credit assignment: how to allocate the global rewards for individual agent policies for better coordination towards maximizing system-level's benefits. In this paper, we propose a new method called Q-value Path Decomposition (QPD) to decompose the system's global Q-values into individual agents' Q-values. Unlike previous works which restrict the representation relation of the individual Q-values and the global one, we leverage the integrated gradient attribution technique into deep MARL to directly decompose global Q-values along trajectory paths to assign credits for agents. We evaluate QPD on the challenging StarCraft II micromanagement tasks and show that QPD achieves the state-of-the-art performance in both homogeneous and heterogeneous multiagent scenarios compared with existing cooperative MARL algorithms.
Recent successes of value-based multi-agent deep reinforcement learning employ optimism in value function by carefully controlling learning rate(Omidshafiei et al., 2017) or reducing update prob-ability (Palmer et al., 2018). We introduce a de-centralized quantile estimator: Responsible Implicit Quantile Network (RIQN), while robust to teammate-environment interactions, able to reduce the amount of imposed optimism. Upon benchmarking against related Hysteretic-DQN(HDQN) and Lenient-DQN (LDQN), we findRIQN agents more stable, sample efficient and more likely to converge to the optimal policy.
The present paper surveys neural approaches to conversational AI that have been developed in the last few years. We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots. For each category, we present a review of state-of-the-art neural approaches, draw the connection between them and traditional approaches, and discuss the progress that has been made and challenges still being faced, using specific systems and models as case studies.
Chatbot has become an important solution to rapidly increasing customer care demands on social media in recent years. However, current work on chatbot for customer care ignores a key to impact user experience - tones. In this work, we create a novel tone-aware chatbot that generates toned responses to user requests on social media. We first conduct a formative research, in which the effects of tones are studied. Significant and various influences of different tones on user experience are uncovered in the study. With the knowledge of effects of tones, we design a deep learning based chatbot that takes tone information into account. We train our system on over 1.5 million real customer care conversations collected from Twitter. The evaluation reveals that our tone-aware chatbot generates as appropriate responses to user requests as human agents. More importantly, our chatbot is perceived to be even more empathetic than human agents.
There is a need for systems to dynamically interact with ageing populations to gather information, monitor health condition and provide support, especially after hospital discharge or at-home settings. Several smart devices have been delivered by digital health, bundled with telemedicine systems, smartphone and other digital services. While such solutions offer personalised data and suggestions, the real disruptive step comes from the interaction of new digital ecosystem, represented by chatbots. Chatbots will play a leading role by embodying the function of a virtual assistant and bridging the gap between patients and clinicians. Powered by AI and machine learning algorithms, chatbots are forecasted to save healthcare costs when used in place of a human or assist them as a preliminary step of helping to assess a condition and providing self-care recommendations. This paper describes integrating chatbots into telemedicine systems intended for elderly patient after their hospital discharge. The paper discusses possible ways to utilise chatbots to assist healthcare providers and support patients with their condition.
Although chatbots have been very popular in recent years, they still have some serious weaknesses which limit the scope of their applications. One major weakness is that they cannot learn new knowledge during the conversation process, i.e., their knowledge is fixed beforehand and cannot be expanded or updated during conversation. In this paper, we propose to build a general knowledge learning engine for chatbots to enable them to continuously and interactively learn new knowledge during conversations. As time goes by, they become more and more knowledgeable and better and better at learning and conversation. We model the task as an open-world knowledge base completion problem and propose a novel technique called lifelong interactive learning and inference (LiLi) to solve it. LiLi works by imitating how humans acquire knowledge and perform inference during an interactive conversation. Our experimental results show LiLi is highly promising.
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including neural network and template-based models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than other systems. The results highlight the potential of coupling ensemble systems with deep reinforcement learning as a fruitful path for developing real-world, open-domain conversational agents.
Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this paper, we develop a novel experience-driven approach that can learn to well control a communication network from its own experience rather than an accurate mathematical model, just as a human learns a new skill (such as driving, swimming, etc). Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in communication networks; and present a novel and highly effective DRL-based control framework, DRL-TE, for a fundamental networking problem: Traffic Engineering (TE). The proposed framework maximizes a widely-used utility function by jointly learning network environment and its dynamics, and making decisions under the guidance of powerful Deep Neural Networks (DNNs). We propose two new techniques, TE-aware exploration and actor-critic-based prioritized experience replay, to optimize the general DRL framework particularly for TE. To validate and evaluate the proposed framework, we implemented it in ns-3, and tested it comprehensively with both representative and randomly generated network topologies. Extensive packet-level simulation results show that 1) compared to several widely-used baseline methods, DRL-TE significantly reduces end-to-end delay and consistently improves the network utility, while offering better or comparable throughput; 2) DRL-TE is robust to network changes; and 3) DRL-TE consistently outperforms a state-ofthe-art DRL method (for continuous control), Deep Deterministic Policy Gradient (DDPG), which, however, does not offer satisfying performance.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191