At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023), with human evaluations still considered the gold standard. Unfortunately, how to perform human evaluations is also an open problem: differing data collection methods have varying levels of human agreement and statistical sensitivity, resulting in differing amounts of human annotation hours and labor costs. In this work we compare five different crowdworker-based human evaluation methods and find that different methods are best depending on the types of models compared, with no clear winner across the board. While this highlights the open problems in the area, our analysis leads to advice of when to use which one, and possible future directions.
University of Lincoln（林肯大学）；Samsung Research（三星研究院）
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given that the amount of dialogue history and corresponding representations can play an important role in the overall performance of a conversational system. This paper studies the amount of history required by conversational agents for reliably predicting dialogue rewards. The task of dialogue reward prediction is chosen for investigating the effects of v…
School of Informatics（信息学院）；University of Edinburgh（爱丁堡大学）
Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitable corpora. This paper presents a novel method for gathering topical, unstructured conversational data in an efficient way: self-dialogues through crowd-sourcing. Alongside this paper, we include a corpus of 3.6 million words across 23 topics. We argue the utility of the corpus by comparing self-dialogues with standard two-party conversations as well as data from other corpora.
Tencent AI Lab（腾讯AI实验室）；City University of Hong Kong（香港城市大学）
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every single sentence, while ellipsis and anaphora frequently occur in dialogues. To address this problem, we propose the conversational SRL task, where an argument can be the dialogue participants, a phrase in the dialogue history or the current sentence. As the existing SRL datasets are in the sentence level, we manually annotate semantic roles for 3,000 chit-chat dialogues (27,198 sentences) to boost the research in this d…
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform goal-oriented functions, and open-domain dialogue (ODD) systems, which focus on non-goal-oriented chitchat. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation, as easily done by a friendly human assistant. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful. Our paper addresses this problem of fusing TODs and ODDs in multi-turn dialog…
Zurich University of Applied Sciences (ZHAW)（苏黎世应用科学大学）
This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by relatively simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperform…
University of Bamberg（班贝格大学）；Norwegian Computing Center（挪威计算中心）
We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogues in which human participants interact with a robot acting as a receptionist. In contrast to most existing work on dialogue management, GraphWOZ relies on a dialogue state explicitly represented as a dynamic knowledge graph instead of a fixed set of slots. This graph is composed of a varying number of entities (such as individuals, places, events, utterances and mentions) and …
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses. Existing dialogue models pay attention to unilaterally incorporating personal knowledge into the dialog while ignoring the fact that incorporating the personality-related conversation information into personal knowledge taken as the bilateral information flow boosts the quality of the subsequent conversation. Besides, it is indispensable to control personal knowledge utilization over the conversation level. In this paper, we propose a conversation-adaption multi-view per…
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…
Norwegian Computing Center（挪威计算中心）；Universidad Central del Ecuador（厄瓜多尔中央大学）；KU Leuven（鲁汶大学）；imec（比利时微电子研究中心）；Université catholique de Louvain（鲁汶天主教大学）
Neural conversational models require substantial amounts of dialogue data for their parameter estimation and are therefore usually learned on large corpora such as chat forums or movie subtitles. These corpora are, however, often challenging to work with, notably due to their frequent lack of turn segmentation and the presence of multiple references external to the dialogue itself. This paper shows that these challenges can be mitigated by adding a weighting model into the architecture. The weighting model, which is itself estimated from dialogue data, associates each training example to a num…
National Computer System Engineering Research Institute of China（中国国家计算机系统工程研究所）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Emotion Recognition in Conversations (ERC) has gained increasing attention for developing empathetic machines. Recently, many approaches have been devoted to perceiving conversational context by deep learning models. However, these approaches are insufficient in understanding the context due to lacking the ability to extract and integrate emotional clues. In this work, we propose novel Contextual Reasoning Networks (DialogueCRN) to fully understand the conversational context from a cognitive perspective. Inspired by the Cognitive Theory of Emotion, we design multi-turn reasoning modules to ext…
Conversational Machine Reading (CMR) aims at answering questions in a complicated manner. Machine needs to answer questions through interactions with users based on given rule document, user scenario and dialogue history, and ask questions to clarify if necessary. In this paper, we propose a dialogue graph modeling framework to improve the understanding and reasoning ability of machine on CMR task. There are three types of graph in total. Specifically, Discourse Graph is designed to learn explicitly and extract the discourse relation among rule texts as well as the extra knowledge of scenario;…
Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager
ISIR Sorbonne University Paris, France（索邦大学ISIR研究所巴黎，法国）；CNRS/ISIR Sorbonne University Paris, France（法国国家科学研究中心/索邦大学ISIR研究所巴黎，法国）；CNRS/SANPSY Univ. Bordeaux Bordeaux, France（法国国家科学研究中心/SANPSY大学波尔多，法国）
We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arbitrary domains. M2M scales to new tasks with just a task schema and an API client from the dialogue system developer, but it is also customizable to cater to task-specific interactions. Compared to the Wizard-of-Oz approach for data collection, M2M achieves greater diversity and coverage of salient dialogue flows while maintaining the naturalness of individual utterances. In the first phase, a simulated user bot and …
Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations. This paper pushes forward towards a promising paradigm called target-driven recommendation dialogue systems, which is highly desired yet under-explored. We focus on how to naturally lead users to accept the designated targets gradually through conversations. To this end, we propose a Target-driven Conversation Planning (TCP) framework to plan a sequence of dialogue actions and topics, driving the system to transit between different conversation stages proactively. We then apply our TC…
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）；Tencent Inc（腾讯公司）
Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models. However, they generally concatenate the dialogue history directly as the model input to predict the response, which we named as the flat pattern and ignores the dynamic information flow across dialogue utterances. In this work, we propose the DialoFlow model, in which we introduce a dynamic flow mechanism to model the context flow, and design three training objectives to capture the information dynamics across dialogue utterances by a…
This paper describes a recently initiated research project aiming at supporting development of computerised dialogue systems that handle breaches of conversational norms such as the Gricean maxims, which describe how dialogue participants ideally form their utterances in order to be informative, relevant, brief, etc. Our approach is to model dialogue and norms with co-operating distributed grammar systems (CDGSs), and to develop methods to detect breaches and to handle them in dialogue systems for verbal human-robot interaction.
University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究院）
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue conte…
Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are present. In such settings, conversation context can become a key disambiguating factor for detecting the user's request from the assistant. One prominent way of incorporating context is modeling past conversation history like task-oriented dialogue models. However, the nature of email conversations (long form) restricts direct usage of the latest advances in task…
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…
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 majority of current Text-to-Speech (TTS) datasets, which are collections of individual utterances, contain few conversational aspects. In this paper, we introduce DailyTalk, a high-quality conversational speech dataset designed for conversational TTS. We sampled, modified, and recorded 2,541 dialogues from the open-domain dialogue dataset DailyDialog inheriting its annotated attributes. On top of our dataset, we extend prior work as our baseline, where a non-autoregressive TTS is conditioned on historical information in a dialogue. From the baseline experiment with both general and our nov…
Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), e.g., open-ended question, statement of opinion, or request for an opinion, is a key step in Natural Language Understanding (NLU) for conversational agents. While DA classification has been extensively studied in human-human conversations, it has not been sufficiently explored for the emerging open-domain automated conversational agents. Moreover, despite significant advances in utterance-level DA classification, full understanding of dialogue utterances requires conversational context. Ano…
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are insufficient to reflect actual human behaviors in practical spoken dialogue systems. In this paper, we propose Task-oriented Dialogue Data Augmentation (TOD-DA), a novel model-agnostic data augmentation paradigm to boost the robustness of task-oriented dialogue modeling on spoken conversations. The TOD-DA consists of two modules: 1) Dialogue Enrichment to expand …
Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
UNC at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Science and Technology of China（中国科学技术大学）；George Mason University（乔治·马歇尔大学）；Yale University（耶鲁大学）；City University of Hong Kong（香港城市大学）；Rice University（得克萨斯大学奥斯汀分校）
As the field of Spoken Dialogue Systems and Conversational AI grows, so does the need for tools and environments that abstract away implementation details in order to expedite the development process, lower the barrier of entry to the field, and offer a common test-bed for new ideas. In this paper, we present Plato, a flexible Conversational AI platform written in Python that supports any kind of conversational agent architecture, from standard architectures to architectures with jointly-trained components, single- or multi-party interactions, and offline or online training of any conversation…
IBM-Research, Almaden（IBM阿尔马登研究中心）；UC Santa Cruz（加州大学圣克鲁兹分校）
In the last several years, Twitter is being adopted by the companies as an alternative platform to interact with the customers to address their concerns. With the abundance of such unconventional conversation resources, push for developing effective virtual agents is more than ever. To address this challenge, a better understanding of such customer service conversations is required. Lately, there have been several works proposing a novel taxonomy for fine-grained dialogue acts as well as develop algorithms for automatic detection of these acts. The outcomes of these works are providing steppin…
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…
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.
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…
Recent advances in large-scale language modeling and generation have enabled the creation of dialogue agents that exhibit human-like responses in a wide range of conversational scenarios spanning a diverse set of tasks, from general chit-chat to focused goal-oriented discourse. While these agents excel at generating high-quality responses that are relevant to prior context, they suffer from a lack of awareness of the overall direction in which the conversation is headed, and the likelihood of task success inherent therein. Thus, we propose a framework in which dialogue agents can evaluate the …
Foviatech GmbH（Foviatech有限公司）；University of Hamburg（汉堡大学）
Many socio-linguistic cues are used in conversational analysis, such as emotion, sentiment, and dialogue acts. One of the fundamental cues is politeness, which linguistically possesses properties such as social manners useful in conversational analysis. This article presents findings of polite emotional dialogue act associations, where we can correlate the relationships between the socio-linguistic cues. We confirm our hypothesis that the utterances with the emotion classes Anger and Disgust are more likely to be impolite. At the same time, Happiness and Sadness are more likely to be polite. A…
In this paper, we present a multimodal dialogue system for Conversational Image Editing. We formulate our multimodal dialogue system as a Partially Observed Markov Decision Process (POMDP) and trained it with Deep Q-Network (DQN) and a user simulator. Our evaluation shows that the DQN policy outperforms a rule-based baseline policy, achieving 90\% success rate under high error rates. We also conducted a real user study and analyzed real user behavior.
IBM Research AI（IBM研究院人工智能部门）；University of Central Florida（中佛罗里达大学）
We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users. Our extensive subjective and objective evaluations on three large public data corpora demonstrate the effectiveness of our system to deliver knowledge…
Information Sciences Institute（信息科学研究所）；University of Southern California（南加州大学）
Effective dialogue involves grounding, the process of establishing mutual knowledge that is essential for communication between people. Modern dialogue systems are not explicitly trained to build common ground, and therefore overlook this important aspect of communication. Improvisational theater (improv) intrinsically contains a high proportion of dialogue focused on building common ground, and makes use of the yes-and principle, a strong grounding speech act, to establish coherence and an actionable objective reality. We collect a corpus of more than 26,000 yes-and turns, transcribing them f…
Dialogue engines that incorporate different types of agents to converse with humans are popular. However, conversations are dynamic in the sense that a selected response will change the conversation on-the-fly, influencing the subsequent utterances in the conversation, which makes the response selection a challenging problem. We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents by taking into account the conversational history, and propose a \emph{Neural Response Selection} method. The proposed method is trained to pred…
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as Statement, Question, Backchannel, Agreement, Disagreement, and Apology. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue act…
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…
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…
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
School of Computer Science and Technology, Soochow University, China（苏州大学计算机科学与技术学院）；Jiangsu Key Lab of Language Computing, Suzhou（江苏省语言计算重点实验室）；School of Computer and Information Engineering, Henan Normal University, China（河南师范大学计算机与信息工程学院）
