This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data construction method that can automatically assign fine-grained scores for arbitrarily dialogue data. Then we train \textbf{SelF-Eval} with a multi-level contrastive learning schema which helps to distinguish different score levels. Experimental results on multiple benchmarks show that SelF-Eval is highly consistent with human evaluations and better than the state-of-the-art models. We give a detailed analysis of the experiments in this paper. Our code is available on GitHub.
École polytechnique fédérale de Lausanne（洛桑联邦理工学院）
We propose a novel large-scale emotional dialogue dataset, consisting of 1M dialogues retrieved from the OpenSubtitles corpus and annotated with 32 emotions and 9 empathetic response intents using a BERT-based fine-grained dialogue emotion classifier. This work explains the complex pipeline used to preprocess movie subtitles and select good movie dialogues to annotate. We also describe the semi-supervised learning process followed to train a fine-grained emotion classifier to annotate these dialogues. Despite the large set of labels, our dialogue emotion classifier achieved an accuracy of $65\…
Beijing University of Posts and Telecommunications（北京邮电大学）；Data Science Lab, JD.com（京东数据科学实验室）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）
Despite the success of neural dialogue systems in achieving high performance on the leader-board, they cannot meet users' requirements in practice, due to their poor reasoning skills. The underlying reason is that most neural dialogue models only capture the syntactic and semantic information, but fail to model the logical consistency between the dialogue history and the generated response. Recently, a new multi-turn dialogue reasoning task has been proposed, to facilitate dialogue reasoning research. However, this task is challenging, because there are only slight differences between the illo…
National University of Singapore（新加坡国立大学）；Robert Bosch (SEA)（博世（东南亚））；Universidad Politécnica de Madrid（马德里理工大学）；Kriston AI Lab（Kriston人工智能实验室）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Recent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment. However, they either perform turn-level evaluation or look at a single dialogue quality dimension. One would expect a good evaluation metric to assess multiple quality dimensions at the dialogue level. To this end, we are motivated to propose a multi-dimensional dialogue-level metric, which consists of three sub-metrics with each targeting a specific dimension. The sub-metrics are trained with novel self-supervised objectives and exhibit strong correlations with hum…
University of California, Santa Cruz（加州大学圣克鲁斯分校）；IBM Research, Almaden（IBM阿尔马登研究中心）
Given the increasing popularity of customer service dialogue on Twitter, analysis of conversation data is essential to understand trends in customer and agent behavior for the purpose of automating customer service interactions. In this work, we develop a novel taxonomy of fine-grained "dialogue acts" frequently observed in customer service, showcasing acts that are more suited to the domain than the more generic existing taxonomies. Using a sequential SVM-HMM model, we model conversation flow, predicting the dialogue act of a given turn in real-time. We characterize differences between custom…
Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, Peking University（北京大学数据科学中心）；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）；Huawei Cloud（华为云）
EmplifAI: a Fine-grained Dataset for Japanese Empathetic Medical Dialogues in 28 Emotion Labels
Kyoto Institute of Technology, Japan（京都技术大学）；National Institute of Information and Communications Technology (NICT), Japan（信息通信技术国家研究所）；Kyoto University, Japan（京都大学）；Nara Institute of Science and Technology, Japan（奈良科学技术大学）
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…
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…
ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue
University of Chinese Academy of Sciences（中国科学院大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Huawei Technologies Ltd.（华为技术有限公司）；Beijing University of Post and Telecommunications（北京邮电大学）
Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues
Pattern Recognition Center, WeChat AI, Tencent Inc（模式识别中心、微信AI、腾讯公司）；Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所、中国科学院）
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…
Hong Kong University of Science and Technology（香港科技大学）
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient. One common practice for this problem is to share training dialogues between different users and train multiple sequence-to-sequence dialogue models together with transfer learning. However, current sequence-to-sequence transfer learning models operate on the entire sentence, which might cause negative transfer if different personal information from different users is mixed up. We propose a personalized decoder model to transfer finer granularity phrase-level knowled…
Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this task. The sequence representation plays a key role in the learning of matching degree between the dialogue context and the response. However, we observe that different context-response pairs sharing the same context always have a greater similarity in the sequence representations calculated by PLMs, which makes it hard to distinguish positive responses from negative ones. Motivat…
Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level was used to improve the expressiveness of synthesized speech. However, the fine-grained information in the dialogue history at the word level also has an important impact on the prosodic expression of an utterance, which has not been well studied in the prior work. Therefore, we propose a novel expressive conversational TTS model, termed as FCTalker, that lear…
University of Macau（澳门大学）；Baidu Inc（百度公司）；Xiamen University（厦门大学）
Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a controllable dialogue generation model to steer response generation under multi-attribute constraints. Specifically, we define and categorize the commonly used control attributes into global and local ones, which possess different granularities of effects on response generation. Then, we significantly extend the conventional seq2seq framework by introducing a novel two-stage decoder, which first uses a multi-grained style s…
SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；University of Liverpool（利物浦大学）；City University of Hong Kong（香港城市大学）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；China Mobile Research Institute（中国移动研究院）；China Mobile (Suzhou) Software Technology Co., Ltd（中国移动苏州软件技术有限公司）
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）；Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室）
本文提出新任务 Dialogue Element Modeling 和新基准 DEMO，用于全面建模与评估 LLMs 对话系统，并构建了基于模仿学习的 DEMO agent，在对话元素建模及域外任务中表现优异。
Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希·海涅大学）
Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift and the occurrence of new concepts and topics frequently lead to severe performance degradation during inference. In this paper we propose a training strategy to build extractive DST models without the need for fine-grained manual span labels. Two novel input-level dropout methods mitigate the negative impact of sample sparsity. We propose a new model architecture with a unified encoder that s…
Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis
Inner Mongolia University（内蒙古大学）；Center for Language and Speech Processing (CLSP)（语言与语音处理中心）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）
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…
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 …
xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark
National University of Singapore（新加坡国立大学）；Universidad Politécnica de Madrid（马德里理工大学）；Tencent AI Lab（腾讯人工智能实验室）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
DISI - University of Trento（特伦托大学DISI学院）；CIMeC and DISI - University of Trento（特伦托大学CIMeC与DISI学院）
When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate linguistically richer dialogues, since the acquisition of language proficiency takes longer than learning the guessing task. By comparing models playing different games (GuessWhat, GuessWhich, and Mutual Friends), we show that this discrepancy is model- and task-agnostic. We investigate whether and when better language quality could lead to higher task success. We show …
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…
East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）
Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching …
National University of Singapore（新加坡国立大学）；Robert Bosch (SEA)（罗伯特·博世（东南亚）公司）；Kriston AI Lab（克里斯顿人工智能实验室）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
Chatbots are designed to carry out human-like conversations across different domains, such as general chit-chat, knowledge exchange, and persona-grounded conversations. To measure the quality of such conversational agents, a dialogue evaluator is expected to conduct assessment across domains as well. However, most of the state-of-the-art automatic dialogue evaluation metrics (ADMs) are not designed for multi-domain evaluation. We are motivated to design a general and robust framework, MDD-Eval, to address the problem. Specifically, we first train a teacher evaluator with human-annotated data t…
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech recognition errors in practical spoken dialogue systems. This work presents a new benchmark on spoken task-oriented conversations, which is intended to study multi-domain dialogue state tracking and knowledge-grounded dialogue modeling. We report that the existing state-of-the-art models trained on written conversations are not performing well on our spoken d…
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;…
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
ZJU–UIUC Institute（浙大UIUC研究院）；ZJU–Hangzhou Global Scientific and Technological Innovation Center（浙大杭州全球科技创新中心）；College of Computer Science and Technology（计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）
While dialogue remains an important end-goal of natural language research, the difficulty of evaluation is an oft-quoted reason why it remains troublesome to make real progress towards its solution. Evaluation difficulties are actually two-fold: not only do automatic metrics not correlate well with human judgments, but also human judgments themselves are in fact difficult to measure. The two most used human judgment tests, single-turn pairwise evaluation and multi-turn Likert scores, both have serious flaws as we discuss in this work. We instead provide a novel procedure involving comparing tw…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）
Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture to produce better responses but pay little attention to considering the quality of the training data contrastively. In this paper, we propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query. A Rank-aware Calibration (RC) network is designed to construct the multi-level contrastive optimization objectives. Since these objectives are calculated bas…
Tsinghua University（清华大学）；Tencent Inc.（腾讯公司）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；WeChat AI, Tencent Inc.（腾讯微信人工智能部）
How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be two critical issues in building a task-oriented dialogue system. In this paper, we propose a novel manual-guided dialogue scheme to alleviate these problems, where the agent learns the tasks from both dialogue and manuals. The manual is an unstructured textual document that guides the agent in interacting with users and the database during the conversation. Our proposed scheme reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to ada…
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resulting in a significant bias across different models and datasets. Some researchers resort to human judgment experimentation for assessing response quality, which is expensive, time consuming, and not scalable. Moreover, judges tend to evaluate a small number of dialogues, meaning that minor differences in evaluation configuration may lead to dissimilar results. In this paper, we present interpretable metrics for evalu…
McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response quality. Yet having an accurate automatic evaluation procedure is crucial for dialogue research, as it allows rapid prototyping and testing of new models with fewer expensive human evaluations. In response to this challenge, we formulate automatic dialogue evaluation as a learning problem. We present an evaluation model (ADEM) that learns to predict human-like sco…
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…
