Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities in isolation and gauge how well they can express them. But rather than being specialized in one single quality, a good open-domain conversational agent should be able to seamlessly blend them all into one cohesive conversational flow. In this work, we investigate several ways to combine models trained towards isolated capabilities, ranging from simple model aggregation schemes that require minimal additional training, to various forms of multi-task training that encompass several skills at all training stages. We further propose a new dataset, BlendedSkillTalk, to analyze how these capabilities would mesh together in a natural conversation, and compare the performance of different architectures and training schemes. Our experiments show that multi-tasking over several tasks that focus on particular capabilities results in better blended conversation performance compared to models trained on a single skill, and that both unified or two-stage approaches perform well if they are constructed to avoid unwanted bias in skill selection or are fine-tuned on our new task.
Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, despite recent progress in domain adaptation, their reliance on in-domain data still limits their cross-domain scalability. In this paper, we argue that this problem can be addressed by extending current models to reflect and exploit the multi-dimensional nature of human dialogue. We present our multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication and us…
Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills). As the number of these experiences increases, a key problem is the discovery of skills that can be used to address a user's request. In this paper, we focus on conversational skill discovery and present a conversational agent which engages in a dialog with users to help them find the skills that fulfill their needs. To this end, we start with a rule-based agent and improve it by using…
We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (architecture, model and training scheme), and details of its deployment, including safety mechanisms. Human evaluations show its superiority to existing open-domain dialogue agents, including its predece…
How can we test whether state-of-the-art generative models, such as Blender and GPT-3, are good AI teachers, capable of replying to a student in an educational dialogue? Designing an AI teacher test is challenging: although evaluation methods are much-needed, there is no off-the-shelf solution to measuring pedagogical ability. This paper reports on a first attempt at an AI teacher test. We built a solution around the insight that you can run conversational agents in parallel to human teachers in real-world dialogues, simulate how different agents would respond to a student, and compare these c…
There is a multitude of novel generative models for open-domain conversational systems; however, there is no systematic evaluation of different systems. Systematic comparisons require consistency in experimental design, evaluation sets, conversational systems and their outputs, and statistical analysis. We lay out a protocol for the evaluation of conversational models using head-to-head pairwise comparison. We analyze ten recent models that claim state-of-the-art performance using a paired head-to-head performance (win-loss-tie) on five evaluation datasets. Our findings show that DialoGPT and …
Yonsei University（延世大学）；Seoul National University（首尔国立大学）
To build open-domain chatbots that are able to use diverse communicative skills, we propose a novel framework BotsTalk, where multiple agents grounded to the specific target skills participate in a conversation to automatically annotate multi-skill dialogues. We further present Blended Skill BotsTalk (BSBT), a large-scale multi-skill dialogue dataset comprising 300K conversations. Through extensive experiments, we demonstrate that our dataset can be effective for multi-skill dialogue systems which require an understanding of skill blending as well as skill grounding. Our code and data are avai…
While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the lack of modularity. Previous studies adopted a hybrid approach with knowledge-based components either to abstract out domain-specific information or to augment data to cover more diverse patterns. On the contrary, we propose to directly address the problem using recent developments in the space of continual learning for neural models. Specifically, we adopt a d…
The Hong Kong University of Science and Technology（香港科技大学）
Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills. A simple yet unexplored solution is prompt-based few-shot learning (Brown et al. 2020) which does not require gradient-based fine-tuning but inste…
Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses. UKP-ATHENA enables new access paths to our swiftly evolving research area with its massive amounts of scientific information and high turnaround times. UKP-ATHENA's responses connect information from multiple heterogeneous sources which researchers currently have to explore manually one after another. Unlike…
Turn-level user satisfaction is one of the most important performance metrics for conversational agents. It can be used to monitor the agent's performance and provide insights about defective user experiences. Moreover, a powerful satisfaction model can be used as an objective function that a conversational agent continuously optimizes for. While end-to-end deep learning has shown promising results, having access to a large number of reliable annotated samples required by these methods remains challenging. In a large-scale conversational system, there is a growing number of newly developed ski…
This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan's key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on understanding and using conversational acts. To provide engaging conversations, Tartan blends script-like yet dynamic responses with data-based generative and retrieval models. Unique to Tartan is that our dialog manager is modeled as a dynamic Fini…
As single-task accuracy on individual language and image tasks has improved substantially in the last few years, the long-term goal of a generally skilled agent that can both see and talk becomes more feasible to explore. In this work, we focus on leveraging individual language and image tasks, along with resources that incorporate both vision and language towards that objective. We design an architecture that combines state-of-the-art Transformer and ResNeXt modules fed into a novel attentive multimodal module to produce a combined model trained on many tasks. We provide a thorough analysis o…
Harvard School of Engineering and Applied Sciences（哈佛大学工程与应用科学学院）；MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in dialog. In this study, we analyze the internal representations learned by neural open-domain dialog systems and evaluate the quality of these representations for learning basic conversational skills. Our results suggest that standard open-domain dialog systems struggle with answering questions, inferring contradiction, and determining the topic of conversation, …
ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation
University of Science and Technology of China（中国科学技术大学）；Singapore Management University（新加坡管理大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
The Hong Kong University of Science and Technology（香港科技大学）
This thesis investigates the controllability of deep learning-based, end-to-end, generative dialogue systems in both task-oriented and chit-chat scenarios. In particular, we study the different aspects of controlling generative dialogue systems, including controlling styles and topics and continuously adding and combining dialogue skills. In the three decades since the first dialogue system was commercialized, the basic architecture of such systems has remained substantially unchanged, consisting of four pipelined basic components, namely, natural language understanding (NLU), dialogue state t…
Current state-of-the-art large-scale conversational AI or intelligent digital assistant systems in industry comprises a set of components such as Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). For some of these systems that leverage a shared NLU ontology (e.g., a centralized intent/slot schema), there exists a separate skill routing component to correctly route a request to an appropriate skill, which is either a first-party or third-party application that actually executes on a user request. The skill routing component is needed as there are thousands of skills t…
Despite recent advances in natural language understanding and generation, and decades of research on the development of conversational bots, building automated agents that can carry on rich open-ended conversations with humans "in the wild" remains a formidable challenge. In this work we develop a real-time, open-ended dialogue system that uses reinforcement learning (RL) to power a bot's conversational skill at scale. Our work pairs the succinct embedding of the conversation state generated using SOTA (supervised) language models with RL techniques that are particularly suited to a dynamic ac…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
Considerable progress has been made towards conversational models that generate coherent and fluent responses by training large language models on large dialogue datasets. These models have little or no control of the generated responses and miss two important features: continuous dialogue skills integration and seamlessly leveraging diverse knowledge sources. In this paper, we propose the Adapter-Bot, a dialogue model that uses a fixed backbone conversational model such as DialGPT (Zhang et al., 2019) and triggers on-demand dialogue skills (e.g., emphatic response, weather information, movie …
Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision signal required to train such models, ideas such as human annotation, replication of a rule-based system, relabeling based on user paraphrases, and bandit-based learning were suggested. However, these approaches: (a) do not scale in terms of the number of skills and skill on-boarding, (b) require a very costly expert annotation/rule-design, (c) introduce ris…
Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orchestrate multiple independently trained dialog agents, or skills, to create a unified system is of particular significance. In this work, we study the task of online posterior dialog orchestration, where we define posterior orchestration as the task of selecting a subset of skills which most appropriately answer a user input using features extracted from both the user input and the individual skills. To account for the various costs associated with extract…
Playpen: An Environment for Exploring Learning Through Conversational Interaction
University of Potsdam（波恩大学）；University of Trento（特伦特大学）；Saarland University（萨尔大学）；ETH Zurich（苏黎世联邦理工学院）；Amsterdam UMC（阿姆斯特丹医疗中心）；Free University of Bozen Bolzano（博兹纳自由大学）；University of Amsterdam（阿姆斯特丹大学）；Heriot-Watt University（赫里奥特-瓦特大学）；DFKI（德意志联邦研究所）；UCL（伦敦大学学院）；University of Edinburgh（爱丁堡大学）
Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting to new information, and improving their performance. In this work we study how to improve internet-driven conversational skills in such a learning framework. We collect deployment data, which we make publicly available, of human interactions, and collect various types of human feedback -- including binary quality measurements, free-form text feedback, and fi…
Customer service is a setting that calls for empathy in live human agent responses. Recent advances have demonstrated how open-domain chatbots can be trained to demonstrate empathy when responding to live human utterances. We show that a blended skills chatbot model that responds to customer queries is more likely to resemble actual human agent response if it is trained to recognize emotion and exhibit appropriate empathy, than a model without such training. For our analysis, we leverage a Twitter customer service dataset containing several million customer<->agent dialog examples in customer …
Towards Conversational AI for Human-Machine Collaborative MLOps
Innov-Acts Ltd（Innov-Acts公司）；Dept. of Digital Systems（数字系统系）；University of Piraeus（比雷埃克斯大学）；Dept. of Informatics and Telematics（信息与电信学系）；Harokopio University（哈罗科比奥大学）
Facebook AI Research（脸书人工智能研究院）；AI2 Incubator（AI2孵化器）
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that …
