Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones. In this paper, we propose EVA, a Chinese dialogue system that contains the largest Chinese pre-trained dialogue model with 2.8B parameters. To build this model, we collect the largest Chinese dialogue dataset named WDC-Dialogue from various public social media. This dataset contains 1.4B context-response pairs and is used as the pre-training corpus of EVA. Extensive experiments on automatic and human evaluation show that EVA outperforms other Chinese pre-trained dialogue models especially in the multi-turn interaction of human-bot conversations.
Tsinghua University（清华大学）；Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts at both user and system sides. About 60% of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across dom…
Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China（中国哈尔滨工业大学社会计算与信息检索研究中心）；Joint Laboratory of HIT and iFLYTEK, iFLYTEK Research, Hefei, China（中国合肥科大讯飞研究院，哈工大讯飞联合实验室）
In this paper, we introduce the first evaluation of Chinese human-computer dialogue technology. We detail the evaluation scheme, tasks, metrics and how to collect and annotate the data for training, developing and test. The evaluation includes two tasks, namely user intent classification and online testing of task-oriented dialogue. To consider the different sources of the data for training and developing, the first task can also be divided into two sub tasks. Both the two tasks are coming from the real problems when using the applications developed by industry. The evaluation data is provided…
This paper presents a large-scale corpus for non-task-oriented dialogue response selection, which contains over 27K distinct prompts more than 82K responses collected from social media. To annotate this corpus, we define a 5-grade rating scheme: bad, mediocre, acceptable, good, and excellent, according to the relevance, coherence, informativeness, interestingness, and the potential to move a conversation forward. To test the validity and usefulness of the produced corpus, we compare various unsupervised and supervised models for response selection. Experimental results confirm that the propose…
Shanghai Jiao Tong University（上海交通大学）；Shanghai Mental Health Center（上海市精神卫生中心）；Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）
In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialogue system is distinguished from existing single-purpose human-machine dialog systems, as it combines task-oriented and chit-chats with uniqueness in dialogue topics and procedures. However, due to the social stigma associated with mental illness, the dialogue data related to depression consultation and diagnosis are rarely disclosed. Based on clinical depression diagnostic criteria …
Dialogue contradiction is a critical issue in open-domain dialogue systems. The contextualization nature of conversations makes dialogue contradiction detection rather challenging. In this work, we propose a benchmark for Contradiction Detection in Chinese Conversations, namely CDConv. It contains 12K multi-turn conversations annotated with three typical contradiction categories: Intra-sentence Contradiction, Role Confusion, and History Contradiction. To efficiently construct the CDConv conversations, we devise a series of methods for automatic conversation generation, which simulate common us…
Due to the unfamiliarity to particular words(or proper nouns) for ingredients, non-native English speakers can be extremely confused about the ordering process in restaurants like Subway. Thus, We developed a dialogue system, which supports Chinese(Mandarin)1 and English2 at the same time. In other words, users can switch arbitrarily between Chinese(Mandarin) and English as the conversation is being conducted. This system is specifically designed for Subway ordering3. In BilDOS, we designed a Discriminator module to tell the language is being used in inputted user utterance, a Translator modul…
Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant problem due to the absence of a standard dataset and evaluation policy. To address this problem, we proposed ViWOZ, a fully-annotated Vietnamese task-oriented dialogue dataset. ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language. The dataset consists of a total of 5,000 dialogues, including 60,946 fully an…
The Chinese University of Hong Kong（香港中文大学）；Communication University of China（中国传媒大学）；Fudan University（复旦大学）
Compared with CrossWOZ (Chinese) and MultiWOZ (English) dataset which have coarse-grained information, there is no dataset which handle fine-grained and hierarchical level information properly. In this paper, we publish a first Cantonese knowledge-driven Dialogue Dataset for REStaurant (KddRES) in Hong Kong, which grounds the information in multi-turn conversations to one specific restaurant. Our corpus contains 0.8k conversations which derive from 10 restaurants with various styles in different regions. In addition to that, we designed fine-grained slots and intents to better capture semantic…
CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）
Beijing University of Posts and Telecommunications（北京邮电大学）
The goal of building intelligent dialogue systems has largely been separately pursued under two motives: task-oriented dialogue (TOD) systems, and open-domain systems for chit-chat (CC). Although previous TOD dialogue systems work well in the testing sets of benchmarks, they would lead to undesirable failure when being exposed to natural scenarios in practice, where user utterances can be of high motive-diversity that fusing both TOD and CC in multi-turn interaction. Since an industrial TOD system should be able to converse with the user between TOD and CC motives, constructing a fuse-motive d…
Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN. MedDialog-EN is an English dataset containing 0.3 million conversations between patients and doctors and 0.5 million utterances. MedDialog-CN is an Chinese dataset containing 1.1 million conversations and 4 million utterances. To our best knowledge, MedDialog-(EN,CN) are…
Knowledge of users' emotion states helps improve human-computer interaction. In this work, we presented EmoNet, an emotion detector of Chinese daily dialogues based on deep convolutional neural networks. In order to maintain the original linguistic features, such as the order, commonly used methods like segmentation and keywords extraction were not adopted, instead we increased the depth of CNN and tried to let CNN learn inner linguistic relationships. Our main contribution is that we presented a new model and a new pipeline which can be used in multi-language environment to solve sentimental …
Hunan University（湖南大学）；JD Technology（京东科技）；Xiangya Hospital of Central South University（中南大学湘雅医院）
Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects. This paper presents our proposed framework for the Chinese MDG organized by the 2021 China conference on knowledge graph and semantic computing (CCKS) competition, which requires generating context-consistent and medically meaningful responses conditioned on the dialogue history. In our framework, we propose a pipeline system composed of entity pre…
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy. To this end, we introduce PLATO-K based on two-stage dialogic learning to strengthen internal knowledge memorization and external knowledge exploitation. In the first stage, PLATO-K learns through massive dialogue corpora and memorizes essential knowledge into model parameters. In the second stage, PLATO-K mimics human beings to search for external information and to leverage the knowledge in response generation. Extensive experiments reve…
In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. Each dialogue is labeled with comprehensive di…
East China University of Science and Technology（华东理工大学）；Tongji University（同济大学）
The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure for downstream tasks is particularly challenging. Firstly, the states need to be able to represent compound entities such as symptoms with their body part or diseases with degrees of severity to provide enough information for decision support. Secondly, these named entities in the utterance might be discontinuous and scattered across sentences and speakers. …
DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Wuhan AI Research（武汉人工智能研究院）；GWM AI Lab（长城汽车人工智能实验室）
Crosstalk, also known by its Chinese name xiangsheng, is a traditional Chinese comedic performing art featuring jokes and funny dialogues, and one of China's most popular cultural elements. It is typically in the form of a dialogue between two performers for the purpose of bringing laughter to the audience, with one person acting as the leading comedian and the other as the supporting role. Though general dialogue generation has been widely explored in previous studies, it is unknown whether such entertaining dialogues can be automatically generated or not. In this paper, we for the first time…
Large-scale open-domain dialogue systems such as PLATO-2 have achieved state-of-the-art scores in both English and Chinese. However, little work explores whether such dialogue systems also work well in the Japanese language. In this work, we create a large-scale Japanese dialogue dataset, Dialogue-Graph, which contains 1.656 million dialogue data in a tree structure from News, TV subtitles, and Wikipedia corpus. Then, we train PLATO-2 using Dialogue-Graph to build a large-scale Japanese dialogue system, PLATO-JDS. In addition, to improve the PLATO-JDS in the topic switch issue, we introduce a …
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；The MOE Key Laboratory of Computational Linguistics, Peking University（北京大学计算语言学教育部重点实验室）；Ecole Polytechnique（巴黎综合理工学院）
Crosstalk is a traditional Chinese theatrical performance art. It is commonly performed by two performers in the form of a dialogue. With the typical features of dialogues, crosstalks are also designed to be hilarious for the purpose of amusing the audience. In this study, we introduce CrossDial, the first open-source dataset containing most classic Chinese crosstalks crawled from the Web. Moreover, we define two new tasks, provide two benchmarks, and investigate the ability of current dialogue generation models in the field of crosstalk generation. The experiment results and case studies demo…
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…
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…
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…
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…
McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）
We investigate evaluation metrics for dialogue response generation systems where supervised labels, such as task completion, are not available. Recent works in response generation have adopted metrics from machine translation to compare a model's generated response to a single target response. We show that these metrics correlate very weakly with human judgements in the non-technical Twitter domain, and not at all in the technical Ubuntu domain. We provide quantitative and qualitative results highlighting specific weaknesses in existing metrics, and provide recommendations for future developme…
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…
UNED（西班牙国立远程教育大学）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；LIMSI（法国计算机科学与自动化研究所）；Zurich University of Applied Sciences (ZHAW)（苏黎世应用科技大学）
In this paper we survey the methods and concepts developed for the evaluation of dialogue systems. Evaluation is a crucial part during the development process. Often, dialogue systems are evaluated by means of human evaluations and questionnaires. However, this tends to be very cost and time intensive. Thus, much work has been put into finding methods, which allow to reduce the involvement of human labour. In this survey, we present the main concepts and methods. For this, we differentiate between the various classes of dialogue systems (task-oriented dialogue systems, conversational dialogue …
Human conversations are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context…
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.
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…
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…
Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size considering the complexity of the dialogues. Additionally, conventional training signal inference is not suitable for non-deterministic agent behaviour, i.e. considering multiple actions as valid in identical dialogue states. We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-determini…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations. In this paper, we propose a Chinese multi-domain knowledge-driven conversation dataset, KdConv, which grounds the topics in multi-turn conversations to knowledge graphs. Our corpus contains 4.5K conversations from three domains (film, music, and travel), and 86K utterances with an average turn number of 19.0. These conversations contain in-depth discussions on related topics and natural transition …
The recent application of RNN encoder-decoder models has resulted in substantial progress in fully data-driven dialogue systems, but evaluation remains a challenge. An adversarial loss could be a way to directly evaluate the extent to which generated dialogue responses sound like they came from a human. This could reduce the need for human evaluation, while more directly evaluating on a generative task. In this work, we investigate this idea by training an RNN to discriminate a dialogue model's samples from human-generated samples. Although we find some evidence this setup could be viable, we …
College of Systems Engineering, National University of Defense Technology（国防科技大学系统工程学院）
Evaluating the quality of a dialogue system is an understudied problem. The recent evolution of evaluation method motivated this survey, in which an explicit and comprehensive analysis of the existing methods is sought. We are first to divide the evaluation methods into three classes, i.e., automatic evaluation, human-involved evaluation and user simulator based evaluation. Then, each class is covered with main features and the related evaluation metrics. The existence of benchmarks, suitable for the evaluation of dialogue techniques are also discussed in detail. Finally, some open issues are …
In open-domain dialogues, predictive uncertainties are mainly evaluated in a domain shift setting to cope with out-of-distribution inputs. However, in real-world conversations, there could be more extensive distributional shifted inputs than the out-of-distribution. To evaluate this, we first propose two methods, Unknown Word (UW) and Insufficient Context (IC), enabling gradual distributional shifts by corruption on the dialogue dataset. We then investigate the effect of distributional shifts on accuracy and calibration. Our experiments show that the performance of existing uncertainty estimat…
National Laboratory of Pattern Recognition, Institute of Automation, CAS（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd（中科凡语科技有限公司凡语AI实验室）
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer's issues and service progress. These applications require summaries to contain the perspective of a single speaker and have a clear topic flow structure, while neither are available in existing datasets. Therefore, in this paper, we introduce a novel Chinese dataset for Customer Service Dialogue Summarization (CSDS). CSDS improves the abstractive summaries in two aspects: (1) In addition to the overall sum…
With the development of the Internet, more and more people get accustomed to online shopping. When communicating with customer service, users may express their requirements by means of text, images, and videos, which precipitates the need for understanding these multimodal information for automatic customer service systems. Images usually act as discriminators for product models, or indicators of product failures, which play important roles in the E-commerce scenario. On the other hand, detailed information provided by the images is limited, and typically, customer service systems cannot under…
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Samsung Research China - Beijing (SRC-B)（三星中国研究院-北京）
The advancements of neural dialogue generation models show promising results on modeling short-text conversations. However, training such models usually needs a large-scale high-quality dialogue corpus, which is hard to access. In this paper, we present a large-scale cleaned Chinese conversation dataset, LCCC, which contains a base version (6.8million dialogues) and a large version (12.0 million dialogues). The quality of our dataset is ensured by a rigorous data cleaning pipeline, which is built based on a set of rules and a classifier that is trained on manually annotated 110K dialogue pairs…
