We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks. With a focus on fast, real-time performance, TRACE tracks the speech, actions, gestures, and visual attention of participants, uses these multimodal inputs to determine the set of task-relevant propositions that have been raised as the dialogue progresses, and tracks the group's epistemic position and beliefs toward them as the task unfolds. Amid increased interest in AI systems that can mediate collaborations, TRACE represents an important step forward for agents that can engage with multiparty, multimodal discourse.
U.S. Army Research Laboratory（美国陆军研究实验室）；Tufts University（塔夫茨大学）；U.S. Naval Research Laboratory（美国海军研究实验室）
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world. To better understand this problem, we need data about asking questions in situated task-based interactions. To this end, we present the Human-Robot Dialogue Learning (HuRDL) Corpus - a novel dialogue corpus collected in an online interactive virtual environment in which human participants play the role of a robot performing a collaborative tool-organization task. We describe the corpus data and a corresponding annotation scheme …
VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；National Key Laboratory of General Artificial Intelligence（通用人工智能全国重点实验室）
DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）；U.S. Naval Research Laboratory（美国海军研究实验室）；Tufts University（塔夫茨大学）
Dialogue agents that interact with humans in situated environments need to manage referential ambiguity across multiple modalities and ask for help as needed. However, it is not clear what kinds of questions such agents should ask nor how the answers to such questions can be used to resolve ambiguity. To address this, we analyzed dialogue data from an interactive study in which participants controlled a virtual robot tasked with organizing a set of tools while engaging in dialogue with a live, remote experimenter. We discovered a number of novel results, including the distribution of question …
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
The demand for multimodal dialogue systems has been rising in various domains, emphasizing the importance of interpreting multimodal inputs from conversational and situational contexts. We explore three methods to tackle this problem and evaluate them on the largest situated dialogue dataset, SIMMC 2.1. Our best method, scene-dialogue alignment, improves the performance by ~20% F1-score compared to the SIMMC 2.1 baselines. We provide analysis and discussion regarding the limitation of our methods and the potential directions for future works. Our code is publicly available at https://github.co…
To tackle the vocabulary problem in conversational systems, previous work has applied unsupervised learning approaches on co-occurring speech and eye gaze during interaction to automatically acquire new words. Although these approaches have shown promise, several issues related to human language behavior and human-machine conversation have not been addressed. First, psycholinguistic studies have shown certain temporal regularities between human eye movement and language production. While these regularities can potentially guide the acquisition process, they have not been incorporated in the pr…
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of Cincinnati（辛辛那提大学）
Reference resolution, which aims to identify entities being referred to by a speaker, is more complex in real world settings: new referents may be created by processes the agents engage in and/or be salient only because they belong to the shared physical setting. Our focus is on resolving references to visualizations on a large screen display in multimodal dialogue; crucially, reference resolution is directly involved in the process of creating new visualizations. We describe our annotations for user references to visualizations appearing on a large screen via language and hand gesture and als…
Confusion is a mental state triggered by cognitive disequilibrium that can occur in many types of task-oriented interaction, including Human-Robot Interaction (HRI). People may become confused while interacting with robots due to communicative or even task-centred challenges. To build a smooth and engaging HRI, it is insufficient for an agent to simply detect confusion; instead, the system should aim to mitigate the situation. In light of this, in this paper, we present our approach to a linguistic design of dialogue policies to build a dialogue framework to alleviate interlocutor confusion. W…
MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Iowa State University（爱荷华州立大学）；Yuanpei College, Peking University（北京大学元培学院）；Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Department of Automation, Tsinghua University（清华大学自动化系）
Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we leverage multi-task learning techniques to train a GPT-2 based model on a more challenging dataset with multiple domains, multiple modalities, and more diversity in output formats. Using only a single model, our method achieves better performance on all sub-tasks, across domains, compared to task and domain-specific models. Furthermore, we evaluated several pr…
DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning
Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Yuanpei College, Peking University（北京大学元培学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；School of Intelligence Science and Technology, Peking University（北京大学智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）
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 …
Georgia Institute of Technology（佐治亚理工学院）；Allen Institute for AI（艾伦人工智能研究所）
We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text adventure game wherein an agent perceives and interacts with the world through textual natural language. Goals in this environment take the form of character-based quests, consisting of personas and motivations. We augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of steadily increasing difficulty for training agent…
University of Potsdam（波茨坦大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
In visual instruction-following dialogue games, players can engage in repair mechanisms in face of an ambiguous or underspecified instruction that cannot be fully mapped to actions in the world. In this work, we annotate Instruction Clarification Requests (iCRs) in CoDraw, an existing dataset of interactions in a multimodal collaborative dialogue game. We show that it contains lexically and semantically diverse iCRs being produced self-motivatedly by players deciding to clarify in order to solve the task successfully. With 8.8k iCRs found in 9.9k dialogues, CoDraw-iCR (v1) is a large spontaneo…
SCOUT: A Situated and Multi-Modal Human-Robot Dialogue Corpus
DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）；DARPA（国防高级研究计划局）；Oak Ridge Associated Universities（橡树岭联合大学）；USC Institute for Creative Technologies（南加州大学创意技术研究所）；Vrije Universiteit（阿姆斯特丹自由大学）
Beijing University of Posts and Telecommunications（北京邮电大学）；The University of Tokyo（东京大学）
In dialogue state tracking, dialogue history is a crucial material, and its utilization varies between different models. However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated. Apparently, it requires different dialogue history to update different slots in different turns. Therefore, using consistent dialogue contents may lead to insufficient or redundant information for different slots, which affects the overall performance. To address this problem, we devis…
Conflict prediction in communication is integral to the design of virtual agents that support successful teamwork by providing timely assistance. The aim of our research is to analyze discourse to predict collaboration success. Unfortunately, resource scarcity is a problem that teamwork researchers commonly face since it is hard to gather a large number of training examples. To alleviate this problem, this paper introduces a multi-feature embedding (MFeEmb) that improves the generalizability of conflict prediction models trained on dialogue sequences. MFeEmb leverages textual, structural, and …
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, AAIS, Peking University（北京大学人工智能研究院数据科学中心）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained language models (PLMs) which presents obstacles to exploiting the power of large-scale pre-training; and (2) the necessity of taking into account the complementarity of various modalities throughout the reasoning process. Although having made remarkable progress in video-grounded dialogue generation, existing methods still fall short when it comes to integrating…
We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share. Therefore, the agents should pool their information and communicate pragmatically to solve the task. Our dialogue agent accurately grounds referents from the partner's utterances using a structured reference resolver, conditions on these referents using a recurrent memory, and uses a pragmatic generation procedure to ens…
Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in order to provide a proper interactive experience, and better understand users' goals. In this paper, we propose a novel multimodal conversational framework, where the dialogue agent's next action and their arguments are derived jointly conditioned both on the conversational and the visual context. Specifically, we propose a new model, that can reason over the…
We describe a corpus-based investigation of proposals in dialogue. First, we describe our DRI compliant coding scheme and report our inter-coder reliability results. Next, we test several hypotheses about what constitutes a well-formed proposal.
In this paper, we argue for the need to distinguish between task and dialogue initiatives, and present a model for tracking shifts in both types of initiatives in dialogue interactions. Our model predicts the initiative holders in the next dialogue turn based on the current initiative holders and the effect that observed cues have on changing them. Our evaluation across various corpora shows that the use of cues consistently improves the accuracy in the system's prediction of task and dialogue initiative holders by 2-4 and 8-13 percentage points, respectively, thus illustrating the generality …
We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some tasks themselves, and requires the system to effectively recover from errors as the user strategically assigns it new goals. We build a game environment to study this scenario, and learn to map user instructions to system actions. We introduce a learning approach focused on recovery from cascading errors between instructions, and modeling methods to explici…
This paper presents a plan-based architecture for response generation in collaborative consultation dialogues, with emphasis on cases in which the system (consultant) and user (executing agent) disagree. Our work contributes to an overall system for collaborative problem-solving by providing a plan-based framework that captures the {\em Propose-Evaluate-Modify} cycle of collaboration, and by allowing the system to initiate subdialogues to negotiate proposed additions to the shared plan and to provide support for its claims. In addition, our system handles in a unified manner the negotiation of…
U.S. Army Research Laboratory（美国陆军研究实验室）；Tufts University（塔夫茨大学）；USC Institute for Creative Technologies（南加州大学创意技术研究所）
ScoutBot is a dialogue interface to physical and simulated robots that supports collaborative exploration of environments. The demonstration will allow users to issue unconstrained spoken language commands to ScoutBot. ScoutBot will prompt for clarification if the user's instruction needs additional input. It is trained on human-robot dialogue collected from Wizard-of-Oz experiments, where robot responses were initiated by a human wizard in previous interactions. The demonstration will show a simulated ground robot (Clearpath Jackal) in a simulated environment supported by ROS (Robot Operating…
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）
With the development of deep learning, advanced dialogue generation methods usually require a greater amount of computational resources. One promising approach to obtaining a high-performance and lightweight model is knowledge distillation, which relies heavily on the pre-trained powerful teacher. Collaborative learning, also known as online knowledge distillation, is an effective way to conduct one-stage group distillation in the absence of a well-trained large teacher model. However, previous work has a severe branch homogeneity problem due to the same training objective and the independent …
Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely
Computational Linguistics, Department of Linguistics University of Potsdam（语言学计算系，语言学系 柏林洪堡大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））
METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues
National University of Singapore（新加坡国立大学）；Nankai University（南开大学）；Sichuan University（四川大学）；School of Artificial Intelligence, Beihang University（北航人工智能学院）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算高级创新中心）；Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB)（数学、信息学与行为语义学重点实验室（LMIB））；Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China（教育部机器学习与工业智能工程研究中心，中国）
METRO 通过大规模语言模型从原始 transcripts 自动诱导策略动作和规划逻辑，提出策略森林结构，实验显示其在两个基准上性能优越，具有跨任务迁移能力。
This paper shows how agents' choice in communicative action can be designed to mitigate the effect of their resource limits in the context of particular features of a collaborative planning task. I first motivate a number of hypotheses about effective language behavior based on a statistical analysis of a corpus of natural collaborative planning dialogues. These hypotheses are then tested in a dialogue testbed whose design is motivated by the corpus analysis. Experiments in the testbed examine the interaction between (1) agents' resource limits in attentional capacity and inferential capacity;…
In dialogues in which both agents are autonomous, each agent deliberates whether to accept or reject the contributions of the current speaker. A speaker cannot simply assume that a proposal or an assertion will be accepted. However, an examination of a corpus of naturally-occurring problem-solving dialogues shows that agents often do not explicitly indicate acceptance or rejection. Rather the speaker must infer whether the hearer understands and accepts the current contribution based on indirect evidence provided by the hearer's next dialogue contribution. In this paper, I propose a model of t…
We present the first complete attempt at concurrently training conversational agents that communicate only via self-generated language. Using DSTC2 as seed data, we trained natural language understanding (NLU) and generation (NLG) networks for each agent and let the agents interact online. We model the interaction as a stochastic collaborative game where each agent (player) has a role ("assistant", "tourist", "eater", etc.) and their own objectives, and can only interact via natural language they generate. Each agent, therefore, needs to learn to operate optimally in an environment with multip…
University of Alberta（阿尔伯塔大学）；Google Brain（谷歌大脑）；Google Translate（谷歌翻译）
We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on an interesting story in that universe, through a series of natural dialogue exchanges. Our model can augment any probabilistic conversational agent by allowing it to reason about universe information established and what potential next utterances might reveal. Ideally, with each utterance, agents would reveal just enough information to add specificity and red…
A discourse strategy is a strategy for communicating with another agent. Designing effective dialogue systems requires designing agents that can choose among discourse strategies. We claim that the design of effective strategies must take cognitive factors into account, propose a new method for testing the hypothesized factors, and present experimental results on an effective strategy for supporting deliberation. The proposed method of computational dialogue simulation provides a new empirical basis for computational linguistics.
EPFL（洛桑联邦理工学院）；Polytechnique Institute of Paris（巴黎理工学院）；Télécom Paris（巴黎电信学院）
A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only evaluated on how well they performed, but also on how much they learnt. The main contribution of this work is to propose new automatic measures to study alignment; focusing on verbal (lexical) alignment, and behavioral alignment (when an instruction given by one was followed with concrete actions by another). A second contribution of our work is to study how …
