This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level. Specifically, UBAR is acquired by fine-tuning the large pre-trained unidirectional language model GPT-2 on the sequence of the entire dialog session which is composed of user utterance, belief state, database result, system act, and system response of every dialog turn. Additionally, UBAR is evaluated in a more realistic setting, where its dialog context has access to user utterances and all content it generated such as belief states, system acts, and system responses. Experimental results on the MultiWOZ datasets show that UBAR achieves state-of-the-art performances in multiple settings, improving the combined score of response generation, policy optimization, and end-to-end modeling by 4.7, 3.5, and 9.4 points respectively. Thorough analyses demonstrate that the session-level training sequence formulation and the generated dialog context are essential for UBAR to operate as a fully end-to-end task-oriented dialog system in real life. We also examine the transfer ability of UBAR to new domains with limited data and provide visualization and a case study to illustrate the advantages of UBAR in modeling on a dialog session level.
This paper studies the exposure bias problem in task-oriented dialog systems, where the model's generated content over multiple turns drives the dialog context away from the ground-truth distribution at training time, introducing error propagation and damaging the robustness of the TOD system. To bridge the gap between training and inference for multi-turn task-oriented dialogs, we propose session-level sampling which explicitly exposes the model to sampled generated content of dialog context during training. Additionally, we employ a dropout-based consistency regularization with the masking s…
Tsinghua University（清华大学）；China Mobile Research Institute（中国移动研究院）；Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute（清华大学-中国移动通信集团有限公司联合研究院）
Recently, two approaches, fine-tuning large pre-trained language models and variational training, have attracted significant interests, separately, for semi-supervised end-to-end task-oriented dialog (TOD) systems. In this paper, we propose Variational Latent-State GPT model (VLS-GPT), which is the first to combine the strengths of the two approaches. Among many options of models, we propose the generative model and the inference model for variational learning of the end-to-end TOD system, both as auto-regressive language models based on GPT-2, which can be further trained over a mix of labele…
Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning, decision making, and language generation from absurdly small amounts of task-specific data. In this paper, we demonstrate that recent progress in language modeling pre-training and transfer learning shows promise to overcome this problem. We propose a task-oriented dialogue model that operates solely on text input: it effectively bypasses explicit policy and langu…
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attention Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in MultiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplifi…
This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize the pre-trained multi-context ConveRT model for context representation in a model trained from scratch; and leverage the immediate preceding user utterance for context generation in a model adapted from the pre-trained GPT-2. Both experiments with the MultiWOZ dataset show that contextual information encoded by pre-trained model improves the performance of response ge…
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…
Tsinghua University（清华大学）；China Mobile Research Institute（中国移动研究院）
Recently, there has been progress in supervised funetuning pretrained GPT-2 to build end-to-end task-oriented dialog (TOD) systems. However, online reinforcement learning of a GPT-2 based dialog system (DS), together with a end-to-end user simulator (US), has not ever been explored. Moreover, a drawback with existing GPT-2 based TOD systems is that they mostly employ the whole dialog history as input, which brings inefficiencies in memory and compute. In this paper, we first propose Simplified Generative Architectures (SGA) for DS and US respectively, both based on GPT-2 but using shortened hi…
Tsinghua University（清华大学）；Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute（清华大学-中国移动通信集团有限公司联合研究院）；China Mobile Research Institute（中国移动研究院）
Building user simulators (USs) for reinforcement learning (RL) of task-oriented dialog systems (DSs) has gained more and more attention, which, however, still faces several fundamental challenges. First, it is unclear whether we can leverage pretrained language models to design, for example, GPT-2 based USs, to catch up and interact with the recently advanced GPT-2 based DSs. Second, an important ingredient in a US is that the user goal can be effectively incorporated and tracked; but how to flexibly integrate goal state tracking and develop an end-to-end trainable US for multi-domains has rem…
UC San Diego（加州大学圣地亚哥分校）；CMU（卡内基梅隆大学）；UC Davis（加州大学戴维斯分校）
Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this problem, we aim to develop a medical dialogue system that can provide COVID19-related consultations. We collected two dialogue datasets -- CovidDialog -- (in English and Chinese respectively) containing conversations between doctors and patients about COV…
Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we leverage multi-task learning techniques to train a GPT-2 based model on a more challenging dataset with multiple domains, multiple modalities, and more diversity in output formats. Using only a single model, our method achieves better performance on all sub-tasks, across domains, compared to task and domain-specific models. Furthermore, we evaluated several pr…
University of California Santa Barbara（加州大学圣巴巴拉分校）；Alibaba DAMO Academy（阿里巴巴达摩院）；Tencent AI Lab（腾讯人工智能实验室）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing. However, directly applying this method heavily suffers from the dialogue entity inconsistency caused by the removal of delexicalized tokens, as well as the catastrophic forgetting problem of the pre-trained model during fine-tuning, leading to unsatisfactory performance. To alleviate these problems, we design a novel GPT-Adapter-CopyNet network, whic…
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware responses. Previous research has either predicted the topic first and then generated the relevant response, or simply applied the attention mechanism to all topics, ignoring the joint distribution of the topic prediction and response generation models and resulting in uncontrollable and unrelated responses. In this paper, we propose a joint framework with a top…
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system which is evaluated by human evaluation and a user simulator based automatic evaluation. Different from traditional pipelined approaches where modules are optimized individually and suffer from cascading failure, we propose an end-to-end dialog system that 1) uses Generative Pretraining 2 (GPT-2) as the backbone to jointly solve Natural Language Understandin…
Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GP…
In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which makes models vulnerable to adversarial responses that are semantically similar but not relevant to the dialogue context. Recent studies have shown that leveraging these adversarial responses as negative training samples is useful for improving the discriminating power of the selection model. Nevertheless, collecting human-written adversarial responses is expens…
The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can be used for end-to-end training without relying on dialogue state tracking to track the dialogue history but allowing the language models to generate responses according to the context given as input. This paper conducts a comparative study to show the effectiveness and strength of using recent pretrained models for fine-tuning, such as BART and T5, on endt…
Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Department of Computer Science（计算机科学系）；Ubiquitous Knowledge Processing Lab (UKP Lab)（普适知识处理实验室）
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心）；The Hong Kong University of Science and Technology（香港科技大学）
Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each module with the least amount of samples (i.e., few-shots) given the high cost related to the data collection. The most common and effective technique to solve this problem is transfer learning, where large language models, either pre-trained on text or task-specific data, are fine-tuned on the few samples. These methods require fine-tuning steps and a set of par…
University of Denver（丹佛大学）；Department of Electrical and Computer Engineering, University of Denver（丹佛大学电气与计算机工程系）
Understanding emotions and responding accordingly is one of the biggest challenges of dialog systems. This paper presents EmpTransfo, a multi-head Transformer architecture for creating an empathetic dialog system. EmpTransfo utilizes state-of-the-art pre-trained models (e.g., OpenAI-GPT) for language generation, though models with different sizes can be used. We show that utilizing the history of emotions and other metadata can improve the quality of generated conversations by the dialog system. Our experimental results using a challenging language corpus show that the proposed approach outper…
Challenges of GPT-3-based Conversational Agents for Healthcare
Bonn-Aachen International Center for Information Technology (b-it)（波恩-亚琛国际信息技术中心）；University of Bonn（波恩大学）；University of Marburg（马尔堡大学）；University Hospital Gießen and Marburg (UKGM)（吉森-马尔堡大学医院）
University of Kentucky（肯塔基大学）；University of Central Florida（中佛罗里达大学）
Task-oriented dialog systems enable users to accomplish tasks using natural language. State-of-the-art systems respond to users in the same way regardless of their personalities, although personalizing dialogues can lead to higher levels of adoption and better user experiences. Building personalized dialog systems is an important, yet challenging endeavor and only a handful of works took on the challenge. Most existing works rely on supervised learning approaches and require laborious and expensive labeled training data for each user profile. Additionally, collecting and labeling data for each…
IBM Research AI（IBM研究院）；International Institute of Information Technology, Bangalore（班加罗尔国际信息技术学院）
Popular dialog datasets such as MultiWOZ are created by providing crowd workers an instruction, expressed in natural language, that describes the task to be accomplished. Crowd workers play the role of a user and an agent to generate dialogs to accomplish tasks involving booking restaurant tables, calling a taxi etc. In this paper, we present a data creation strategy that uses the pre-trained language model, GPT2, to simulate the interaction between crowd workers by creating a user bot and an agent bot. We train the simulators using a smaller percentage of actual crowd-generated conversations …
Tsinghua University（清华大学）；China Mobile Research Institute（中国移动研究院）；Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute（清华大学-中国移动通信集团有限公司联合研究院）
Recently, Transformer based pretrained language models (PLMs), such as GPT2 and T5, have been leveraged to build generative task-oriented dialog (TOD) systems. A drawback of existing PLM-based models is their non-Markov architectures across turns, i.e., the whole history is used as the conditioning input at each turn. First, this brings inefficiencies in memory and computation. Furthermore, using the whole history increases model complexity and may hurt the training efficiency, especially when facing small amounts of labeled training data (the low-resource setting). In this paper, motivated by…
Large end-to-end neural open-domain chatbots are becoming increasingly popular. However, research on building such chatbots has typically assumed that the user input is written in nature and it is not clear whether these chatbots would seamlessly integrate with automatic speech recognition (ASR) models to serve the speech modality. We aim to bring attention to this important question by empirically studying the effects of various types of synthetic and actual ASR hypotheses in the dialog history on TransferTransfo, a state-of-the-art Generative Pre-trained Transformer (GPT) based neural open-d…
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…
Capital One - Conversation Research（第一资本 - 对话研究）；Capital One - Center for Machine Learning（第一资本 - 机器学习中心）
Task oriented dialogue (TOD) requires the complex interleaving of a number of individually controllable components with strong guarantees for explainability and verifiability. This has made it difficult to adopt the multi-turn multi-domain dialogue generation capabilities of streamlined end-to-end open-domain dialogue systems. In this paper, we present a new framework, DLGNet-Task, a unified task-oriented dialogue system which employs autoregressive transformer networks such as DLGNet and GPT-2/3 to complete user tasks in multi-turn multi-domain conversations. Our framework enjoys the controll…
The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues
KU Leuven（鲁汶大学）；imec（比利时微电子研究中心）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；King’s College London（伦敦国王学院）；Universidad Central del Ecuador（厄瓜多尔中央大学）；Stanford University（斯坦福大学）
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FewShotWoz, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develo…
Can Large Language Models be Used to Provide Psychological Counselling? An Analysis of GPT-4-Generated Responses Using Role-play Dialogues
The University of Electro-Communications（电气通信大学）；iDEAR Human Support Service（iDEAR人文支持服务）；Japanese Organization of Mental Health and Educational Agencies（日本心理健康与教育机构组织）
The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained in a purely supervised manner, which suffer a significant risk from adversarial attacking (e.g., a nonsensical response that enjoys a high classification score). To alleviate this risk, we propose an adversarial training approach to learn a robust model, ATT (Adversarial Turing Test), that discriminates machine-generated responses from human-written replies. …
The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
Dialog systems enriched with external knowledge can handle user queries that are outside the scope of the supporting databases/APIs. In this paper, we follow the baseline provided in DSTC9 Track 1 and propose three subsystems, KDEAK, KnowleDgEFactor, and Ens-GPT, which form the pipeline for a task-oriented dialog system capable of accessing unstructured knowledge. Specifically, KDEAK performs knowledge-seeking turn detection by formulating the problem as natural language inference using knowledge from dialogs, databases and FAQs. KnowleDgEFactor accomplishes the knowledge selection task by for…
Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning more followup interactions. Current conversational models are increasingly capable of producing turns that are context-relevant, but in order to produce compelling agents, these models need to be able to predict and optimize for turns that are genuinely engaging. We leverage social media feedback data (number of replies and upvotes) to build a large-scale training dataset for feedback prediction. To alleviate possible…
Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate outputs that are factually accurate and complete. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs, namely GPT-4. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two ag…
Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking
ADAPT Centre, Trinity College Dublin（都柏林圣三一学院ADAPT中心）；ADAPT Centre, University College Dublin（都柏林大学学院ADAPT中心）；ADAPT Center, Trinity College Dublin（都柏林圣三一学院ADAPT中心）
