Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process with the entire system vocabulary as action space. Policies trained in such a fashion do not require expert-defined action spaces, but they have to deal with large action spaces and long trajectories, making RL impractical. Using the latent space of a variational model as action space alleviates this problem. However, current approaches use an uninformed prior for training and optimize the latent distribution solely on the context. It is therefore unclear whether the latent representation truly encodes the characteristics of different actions. In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning. We choose response auto-encoding as the auxiliary task, as this captures the generative factors of dialogue responses while requiring low computational cost and neither additional data nor labels. Our approach yields a more action-characterized latent representations which support end-to-end dialogue policy optimization and achieves state-of-the-art success rates. These results warrant a more wide-spread use of RL in end-to-end dialogue models.
NTT Communication Science Laboratories（NTT通信科学实验室）；RIKEN（理化学研究所）；Tohoku University（东北大学）
Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems. This paper introduces the bipartite-play method, a dialogue collection method for automating dialogue system evaluation. It addresses the limitations of existing dialogue collection methods: (i) inability to compare with systems that are not publicly available, and (ii) vulnerability to cheating by intentionally selecting systems to be compared. Experimental results show that the automatic evaluation using the bipartite-play method mitigates these two drawbacks and correlates as stron…
Queen Mary College, University of London（伦敦大学玛丽女王学院）；Constellation AI
We present an automated evaluation method to measure fluidity in conversational dialogue systems. The method combines various state of the art Natural Language tools into a classifier, and human ratings on these dialogues to train an automated judgment model. Our experiments show that the results are an improvement on existing metrics for measuring fluidity.
Automatic dialogue evaluation plays a crucial role in open-domain dialogue research. Previous works train neural networks with limited annotation for conducting automatic dialogue evaluation, which would naturally affect the evaluation fairness as dialogue systems close to the scope of training corpus would have more preference than the other ones. In this paper, we study alleviating this problem from the perspective of continual learning: given an existing neural dialogue evaluator and the next system to be evaluated, we fine-tune the learned neural evaluator by selectively forgetting/updatin…
Sun Yat-Sen University（中山大学）；Dark Matter AI Inc.（暗物质人工智能公司）
Automatically evaluating dialogue coherence is a challenging but high-demand ability for developing high-quality open-domain dialogue systems. However, current evaluation metrics consider only surface features or utterance-level semantics, without explicitly considering the fine-grained topic transition dynamics of dialogue flows. Here, we first consider that the graph structure constituted with topics in a dialogue can accurately depict the underlying communication logic, which is a more natural way to produce persuasive metrics. Capitalized on the topic-level dialogue graph, we propose a new…
Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concep…
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores;…
Sun Yat-Sen University（中山大学）；Soochow University（苏州大学）；Dark Matter AI Inc.（暗物质人工智能公司）
Beyond current conversational chatbots or task-oriented dialogue systems that have attracted increasing attention, we move forward to develop a dialogue system for automatic medical diagnosis that converses with patients to collect additional symptoms beyond their self-reports and automatically makes a diagnosis. Besides the challenges for conversational dialogue systems (e.g. topic transition coherency and question understanding), automatic medical diagnosis further poses more critical requirements for the dialogue rationality in the context of medical knowledge and symptom-disease relations.…
Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4
Universidad Politécnica de Madrid（马德里理工大学）；National University of Singapore（新加坡国立大学）；Tencent AI Lab（腾讯人工智能实验室）；University of Southern California（南加州大学）；New York University（纽约大学）；Carnegie Mellon University（卡内基梅隆大学）
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
University of Southern California / Information Sciences Institute（南加州大学 / 信息科学研究所）；Peking University（北京大学）；AWS AI Labs（AWS AI 实验室）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
University of Southern California（南加州大学）；Information Sciences Institute（信息科学研究所）；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Automatic evaluation is beneficial for open-domain dialog system development. However, standard word-overlap metrics (BLEU, ROUGE) do not correlate well with human judgements of open-domain dialog systems. In this work we propose to use the sentiment of the next user utterance for turn or dialog level evaluation. Specifically we propose three methods: one that predicts the next sentiment directly, and two others that predict the next user utterance using an utterance or a feedback generator model and then classify its sentiment. Experiments show our model outperforming existing automatic evalu…
National University of Singapore（新加坡国立大学）；Universidad Politécnica de Madrid（马德里理工大学）；Robert Bosch (SEA) Pte Ltd（博世（东南亚）私人有限公司）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. This calls for a dedicated network architecture for domain generalization. To tackle the multi-domain dialogue evaluation task, we propose a Panel of Expe…
Automated metrics such as BLEU are widely used in the machine translation literature. They have also been used recently in the dialogue community for evaluating dialogue response generation. However, previous work in dialogue response generation has shown that these metrics do not correlate strongly with human judgment in the non task-oriented dialogue setting. Task-oriented dialogue responses are expressed on narrower domains and exhibit lower diversity. It is thus reasonable to think that these automated metrics would correlate well with human judgment in the task-oriented setting where the …
Research on emotionally intelligent dialogue generation based on automatic dialogue system
University of the People（人民大学）；Sehan University（世翰大学）；Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）；Universidad Internacional Isabel I de Castilla（卡斯蒂利亚伊莎贝尔一世国际大学）；AMA University（AMA大学）
Beijing Institute of Technology（北京理工大学）；Huazhong University of Science and Technology（华中科技大学）
Open-domain generative dialogue systems have attracted considerable attention over the past few years. Currently, how to automatically evaluate them, is still a big challenge problem. As far as we know, there are three kinds of automatic methods to evaluate the open-domain generative dialogue systems: (1) Word-overlap-based metrics; (2) Embedding-based metrics; (3) Learning-based metrics. Due to the lack of systematic comparison, it is not clear which kind of metrics are more effective. In this paper, we will first measure systematically all kinds of automatic evaluation metrics over the same …
Information Sciences Institute（信息科学研究所）；University of Southern California（南加州大学）；College of Natural Sciences（自然科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem. Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given context that share no common words with reference responses. A recent work proposed Referenced metric and Unreferenced metric Blended Evaluation Routine (RUBER) to combine a learning-based metric, which predicts relatedness between a generated response and a given query, with reference-based metric; it showed high correlation with human judgments. In this pa…
We present "AutoJudge", an automated evaluation method for conversational dialogue systems. The method works by first generating dialogues based on self-talk, i.e. dialogue systems talking to itself. Then, it uses human ratings on these dialogues to train an automated judgement model. Our experiments show that AutoJudge correlates well with the human ratings and can be used to automatically evaluate dialogue systems, even in deployed systems. In a second part, we attempt to apply AutoJudge to improve existing systems. This works well for re-ranking a set of candidate utterances. However, our e…
Peking University（北京大学）；Beijing Institute of Big Data Research（北京大数据研究院）
Automatic evaluating the performance of Open-domain dialogue system is a challenging problem. Recent work in neural network-based metrics has shown promising opportunities for automatic dialogue evaluation. However, existing methods mainly focus on monolingual evaluation, in which the trained metric is not flexible enough to transfer across different languages. To address this issue, we propose an adversarial multi-task neural metric (ADVMT) for multi-lingual dialogue evaluation, with shared feature extraction across languages. We evaluate the proposed model in two different languages. Experim…
Meituan（美团）；Beijing University of Posts and Telecommunications（北京邮电大学）
Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which only focus on a few qualities, are hard to evaluate dialogue comprehensively. Furthermore, these metrics lack an effective score composition approach for diverse evaluation qualities. To address the above problems, we propose a Multi-Metric Evaluation based on Correlation Re-Scaling (MME-CRS) for evaluating open-domain dialogue. Firstly, we build an evaluatio…
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Robert Bosch Center for Data Sciences and AI (RBC-DSAI), Indian Institute of Technology, Madras（罗伯特博世数据科学与人工智能中心（RBC-DSAI），印度理工学院马德拉斯分校）；Microsoft, India（微软印度公司）；NVIDIA, India（英伟达印度公司）
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM(Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM …
The article describes the new approach for quality improvement of automated dialogue systems for customer support service. Analysis produced in the paper demonstrates the dependency of the quality of the retrieval-based dialogue system quality on the choice of negative responses. The proposed approach implies choosing the negative samples according to the distribution of responses in the train set. In this implementation the negative samples are randomly chosen from the original response distribution and from the "artificial" distribution of negative responses, such as uniform distribution or …
As conversational AI-based dialogue management has increasingly become a trending topic, the need for a standardized and reliable evaluation procedure grows even more pressing. The current state of affairs suggests various evaluation protocols to assess chat-oriented dialogue management systems, rendering it difficult to conduct fair comparative studies across different approaches and gain an insightful understanding of their values. To foster this research, a more robust evaluation protocol must be set in place. This paper presents a comprehensive synthesis of both automated and human evaluat…
Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when the user's utterance is accepted. But during daily conversations, humans always decide whether to continue to utter an utterance based on the context. Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally. In this paper, we explore the dialogue system that automat…
In contrast with goal-oriented dialogue, social dialogue has no clear measure of task success. Consequently, evaluation of these systems is notoriously hard. In this paper, we review current evaluation methods, focusing on automatic metrics. We conclude that turn-based metrics often ignore the context and do not account for the fact that several replies are valid, while end-of-dialogue rewards are mainly hand-crafted. Both lack grounding in human perceptions.
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…
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…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Data Science Lab, JD.com（京东数据科学实验室）；National Computer network Emergency Response technical Team/Coordination Center of China（国家计算机网络应急技术处理协调中心）
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies greatly. The noise and uneven complexity of query-response pairs impede the learning efficiency and effects of the neural dialogue generation models. What is more, so far, there are no unified dialogue complexity measurements, and the dialogue complexity embodies multiple aspects of attributes---specificity, repetitiveness, relevance, etc. Inspired by human…
We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model …
Research Center for Social Computing and Information Retrieval（社会计算与信息检索研究中心）；Harbin Institute of Technology（哈尔滨工业大学）
Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base. Conversely, sequence-to-sequence models learn to map dialogue history to the response in current turn without explicit knowledge base querying. In this work, we propose a novel framework that leverages the advantages of classic pipeline and sequence-to-sequence models. Our framework models a dialogue state as a fixed-size distributed representation and use this representation to query a knowledge base via an attention …
School of Engineering, Westlake University（西湖大学工学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院前沿技术研究所）；Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology（哈尔滨工业大学社会计算与信息检索研究中心）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）
Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be costly, slow, error-prone, and more importantly, cannot cover the vast range of domains in real-world dialogues for customer service. We propose the task of dialogue state induction, building two neural latent variable models that mine dialogue states automatically from unlabeled customer service dialogue records. Results show that the models can effectively fi…
The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue belief state tracking (summarising conversation history) and dialogue decision-making (deciding how to reply to the user). In this work, we only focus on devising a policy that chooses which dialogue action to respond to the user. The sequential system decision-making process can be abstracted into a partially observable Markov decision process (POMDP). Under…
Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
NetEase Inc.（网易公司）；Tsinghua University（清华大学）；Samsung Research China - Beijing（三星电子中国研究院（北京））；Alibaba Group（阿里巴巴集团）
Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data dilemma, we propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. Specifically, a data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data. A ranking module is employed to filter out low-quality dialogues. Further, …
Utterance interpretation is one of the main functions of a dialogue manager, which is the key component of a dialogue system. We propose the action state update approach (ASU) for utterance interpretation, featuring a statistically trained binary classifier used to detect dialogue state update actions in the text of a user utterance. Our goal is to interpret referring expressions in user input without a domain-specific natural language understanding component. For training the model, we use active learning to automatically select simulated training examples. With both user-simulated and intera…
Dialogue systems without consistent responses are not fascinating. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses using less computational resources than fi…
Cairo University（开罗大学）；Institute of Statistical Studies and Research（统计研究与研究所）
Labelling of user's utterances to understanding his attends which called Dialogue Act (DA) classification, it is considered the key player for dialogue language understanding layer in automatic dialogue systems. In this paper, we proposed a novel approach to user's utterances labeling for Egyptian spontaneous dialogues and Instant Messages using Machine Learning (ML) approach without relying on any special lexicons, cues, or rules. Due to the lack of Egyptian dialect dialogue corpus, the system evaluated by multi-genre corpus includes 4725 utterances for three domains, which are collected and …
National University of Singapore（新加坡国立大学）；New York University（纽约大学）；Intapp Inc.（Intapp公司）；Carnegie Mellon University（卡内基梅隆大学）
The development of Open-Domain Dialogue Systems (ODS)is a trending topic due to the large number of research challenges, large societal and business impact, and advances in the underlying technology. However, the development of these kinds of systems requires two important characteristics:1) automatic evaluation mechanisms that show high correlations with human judgements across multiple dialogue evaluation aspects (with explainable features for providing constructive and explicit feedback on the quality of generative models' responses for quick development and deployment)and 2) mechanisms tha…
Unsupervised dialogue structure learning is an important and meaningful task in natural language processing. The extracted dialogue structure and process can help analyze human dialogue, and play a vital role in the design and evaluation of dialogue systems. The traditional dialogue system requires experts to manually design the dialogue structure, which is very costly. But through unsupervised dialogue structure learning, dialogue structure can be automatically obtained, reducing the cost of developers constructing dialogue process. The learned dialogue structure can be used to promote the di…
Beijing Institute of Technology（北京理工大学）；Huawei Technologies Ltd.（华为技术有限公司）
Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings remains a huge challenge for neural dialogue systems. To alleviate these problems, methods like introducing external information, reconstructing the optimization function, and manipulating data samples are proposed, while they primarily focus on avoiding training with CDM, inevitably weakening the model's ability of understanding CDM in human conversations and limiting further improvements in model performance. This pap…
McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；HEC Montréal（蒙特利尔高等商学院）
An open challenge in constructing dialogue systems is developing methods for automatically learning dialogue strategies from large amounts of unlabelled data. Recent work has proposed Next-Utterance-Classification (NUC) as a surrogate task for building dialogue systems from text data. In this paper we investigate the performance of humans on this task to validate the relevance of NUC as a method of evaluation. Our results show three main findings: (1) humans are able to correctly classify responses at a rate much better than chance, thus confirming that the task is feasible, (2) human performa…
We present the dialogue component of the speech-to-speech translation system VERBMOBIL. In contrast to conventional dialogue systems it mediates the dialogue while processing maximally 50% of the dialogue in depth. Special requirements like robustness and efficiency lead to a 3-layered hybrid architecture for the dialogue module, using statistics, an automaton and a planner. A dialogue memory is constructed incrementally.
There has recently been an explosion of work on spoken dialogue systems, along with an increased interest in open-domain systems that engage in casual conversations on popular topics such as movies, books and music. These systems aim to socially engage, entertain, and even empathize with their users. Since the achievement of such social goals is hard to measure, recent research has used dialogue length or human ratings as evaluation metrics, and developed methods for automatically calculating novel metrics, such as coherence, consistency, relevance and engagement. Here we develop a PARADISE mo…
Salesforce Research（Salesforce研究）；Singapore Management University（新加坡管理大学）；Salesforce Research Asia（Salesforce亚洲研究）
Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself. These approaches have shown good performance gain, especially in complicated dialogue domains with dynamic slot values. However, they fall short in two aspects: (1) they do not allow models to explicitly learn signals across domains and slots to detect potential dependencies among (domain, slot) pairs; and (2) existing models follow auto-regressive approaches which …
This paper presents an automatic method to evaluate the naturalness of natural language generation in dialogue systems. While this task was previously rendered through expensive and time-consuming human labor, we present this novel task of automatic naturalness evaluation of generated language. By fine-tuning the BERT model, our proposed naturalness evaluation method shows robust results and outperforms the baselines: support vector machines, bi-directional LSTMs, and BLEURT. In addition, the training speed and evaluation performance of naturalness model are improved by transfer learning from …
MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems
Faculty of Information Technology, Monash University（墨尔本大学信息科技学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）；School of Science, Computing and Emerging Technologies, Swinburne University of Technology（斯威本理工大学科学、计算与新兴技术学院）
Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and frequently result in uninformative utterances. In this paper, we propose using a dialogue policy to plan the content and style of target responses in the form of an action plan, which includes knowledge sentences related to the dialogue context, targeted dialogue acts, topic information, etc. The attributes within the action plan are obtained by automatically annota…
Ping An Life Insurance of China, Ltd.（中国平安人寿保险股份有限公司）
Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema and asking many domain experts to annotate the corresponding utterances, upon which neural models are trained. This procedure brings the challenges of information sharing hindering, out-of-schema, or data sparsity in open-domain dialogue systems. To tackle these challenges, we explore a new task of {\em automatic intent-slot induction} and propose a novel dom…
We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and semantic grammar - Dynamic Syntax (DS) - allows systems to discover, generate, and understand many new dialogue variants. The method avoids the use of expensive and time-consuming dialogue act annotations, and supports more natural (incremental) dialogues than turn-based systems. Here, language generation and dialogue management are treated as a joint decision/optimisation problem, and …
