Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Breakdown situations in dialogues between humans and socially intelligent agents
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-3036-6519
2023 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Situationer av sammanbrott i dialoger mellan människor och socialt intelligenta agenter (Swedish)
Abstract [en]

Dialogues between humans are complex due to the challenges in predicting how they will unfold as people may want to achieve different purposes. For instance, to act together, they co-create a common goal; to learn, they co-create knowledge; to build relationships, they share emotions and beliefs. Apart from different purposes, people may want to achieve multiple purposes in a dialogue, introducing a movement between goals. Such actions cause problems in understanding and conflicts among the participants. Activity Theory denotes such situations as breakdown situations, which also occur when people have dialogues with software agents driven by Artificial Intelligence (AI). This thesis falls within the domain of human-centred AI, focusing on software agents able to collaborate and support people to achieve their goals. We call these software agents socially intelligent agents.

This thesis has two aims: (1) to develop an increased understanding of breakdown situations in dialogues between humans and socially intelligent agents and (2) to develop computational frameworks based on the developed understanding to manage breakdown situations, which could be embedded in an agent's cognitive architecture. The theoretical frameworks from social sciences, particularly Activity Theory, were applied to address the aims. They provided an alternate perspective that considers breakdown situations as opportunities to learn something new rather than the traditional view of them being errors or failures.

The main contributions addressing the first aim were theory-driven analysis and empirical findings that provided increased knowledge of breakdown situations, resulting in design implications and future agendas guiding the subsequent research. The results informed the three strategies to manage breakdown situations by aligning, partially aligning or not aligning with human's intentions. We found that participants considered partial alignment as a sufficient level of agreement for potential collaboration, which would be interesting to verify in future studies. To address the second aim, two novel computational frameworks were provided. These frameworks were based on linguistics and social sciences theories, allowing an agent to interpret the dialogue's syntax, semantics, and social aspects, facilitating a deeper understanding of dialogues. Finally, a novel computational framework was developed to reason about conflicts and be able to plan by adopting the strategy of aligning with the human's intentions. 

We conceptualised a cognitive architecture based on our research findings. The cognitive architecture embeds mechanisms for socially intelligent agents to manage breakdown situations in dialogues with humans. 

Place, publisher, year, edition, pages
Umeå: Umeå University, 2023. , p. 68
Series
Report / UMINF, ISSN 0348-0542 ; 23.07
Keywords [en]
Dialogues, Breakdown Situations, Focus Shift, Human-Centric Artificial Intelligence, Engeström’s Activity Triangle, We-Intention, Argumentation-Based Dialogues, Grice’s Cooperative Principle, Communicative Functions, Wizard-of-Oz, User Studies, Thematic Analysis, Sequence Organisation
National Category
Human Computer Interaction Language Technology (Computational Linguistics)
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-216752ISBN: 9789180701648 (print)ISBN: 9789180701655 (electronic)OAI: oai:DiVA.org:umu-216752DiVA, id: diva2:1812696
Public defence
2023-12-14, MIT.A.121, MIT-huset, Umeå, 13:00 (English)
Opponent
Supervisors
Available from: 2023-11-23 Created: 2023-11-16 Last updated: 2023-11-20Bibliographically approved
List of papers
1. Younger and Older Adults' Perceptions on Role, Behavior, Goal and Recovery Strategies for Managing Breakdown Situations in Human-Robot Dialogues
Open this publication in new window or tab >>Younger and Older Adults' Perceptions on Role, Behavior, Goal and Recovery Strategies for Managing Breakdown Situations in Human-Robot Dialogues
2021 (English)In: HAI '21: Proceedings of the 9th International Conference on Human-Agent Interaction, ACM Digital Library, 2021, p. 433-437Conference paper, Published paper (Refereed)
Abstract [en]

Mutual understanding of the dialogue purpose and role of participants is vital to co-create meaning and satisfactory outcomes during human and social robot dialogues. This study explored how younger and older adults perceive roles, goals and behaviors of dialogue participants when breakdown situations occur during co-creation of meaning in a dialogue. The aim was to identify intuitive mechanisms that a social robot can use to manage breakdown situations. A set of dialogues were authored, based on activity-theoretical models of human activity and recorded in a Wizard-of-Oz setup with a Nao robot. Results of 8 (four younger and four old adults) participant interviews after observing the recorded dialogues are presented. Thematic analysis of interviews resulted into three themes of perceptions and expectations on roles and relationship, the robot’s understanding of the situation and relevant behavioral norms. Themes were translated into design implications for developing activity-centric dialogue systems to seamlessly manage breakdown situations. Future work includes implementation and further study of the proposed design implications for human robot dialogues.

Place, publisher, year, edition, pages
ACM Digital Library, 2021
Keywords
User Study, Adaptive Interactive Systems, Thematic analysis, Activity theory, Social HRI, Personalisation
National Category
Computer Sciences
Research subject
human-computer interaction
Identifiers
urn:nbn:se:umu:diva-188970 (URN)10.1145/3472307.3484679 (DOI)2-s2.0-85119351981 (Scopus ID)978-1-4503-8620-3 (ISBN)
Conference
HAI 2021, 9th International Conference on Human-Agent Interaction, Online via Nagoya University, Japan, 2021
Funder
EU, Horizon 2020, 952026
Available from: 2021-11-18 Created: 2021-11-18 Last updated: 2023-11-20Bibliographically approved
2. Expecting, understanding, relating, and interacting: older, middle-aged and younger adults' perspectives on breakdown situations in human–robot dialogues
Open this publication in new window or tab >>Expecting, understanding, relating, and interacting: older, middle-aged and younger adults' perspectives on breakdown situations in human–robot dialogues
2022 (English)In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 9, article id 956709Article in journal (Refereed) Published
Abstract [en]

Purpose: The purpose of this study is to explore how older, middle aged and younger adults perceive breakdown situations caused by lack of or inconsistent knowledge, sudden focus shifts, and conflicting intentions in dialogues between a human and a socially intelligent robot in a home environment, and how they perceive strategies to manage breakdown situations.

Methods: Scenarios embedding dialogues on health-related topics were constructed based on activity-theoretical and argumentation frameworks. Different reasons for breakdown situations and strategies to handle these were embedded. The scenarios were recorded in a Wizard-of-Oz setup, with a human actor and a Nao robot. Twenty participants between 23 and 72 years of age viewed the recordings and participated in semi-structured interviews conducted remotely. Data were analyzed qualitatively using thematic analysis.

Results: Four themes relating to breakdown situations emerged: expecting, understanding, relating, and interacting. The themes span complex human activity at different complementary levels and provide further developed understanding of breakdown situations in human–robot interaction (HRI). Older and middle-aged adults emphasized emphatic behavior and adherence to social norms, while younger adults focused on functional aspects such as gaze, response time, and length of utterances. A hierarchical taxonomy of aspects relating to breakdown situations was formed, and design implications are provided, guiding future research.

Conclusion: We conclude that a socially intelligent robot agent needs strategies to 1) construct and manage its understanding related to emotions of the human, social norms, knowledge, and motive on a higher level of meaningful human activity, 2) act accordingly, for instance, adhering to transparent social roles, and 3) resolve conflicting motives, and identify reasons to prevent and manage breakdown situations at different levels of collaborative activity. Furthermore, the novel methodology to frame the dynamics of human–robot dialogues in complex activities using Activity Theory and argumentation theory was instrumental in this work and will guide the future work on tailoring the robot's behavior.}

Place, publisher, year, edition, pages
Frontiers Media S.A., 2022
Keywords
Activity Theory, human–robot interaction, breakdown situations, focus shift, qualitative study, social robotics, argumentation theory
National Category
Robotics Human Computer Interaction
Research subject
human-computer interaction
Identifiers
urn:nbn:se:umu:diva-200444 (URN)10.3389/frobt.2022.956709 (DOI)000884479600001 ()2-s2.0-85141845765 (Scopus ID)
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP), MMW 2019.0220EU, Horizon 2020, 952026
Available from: 2022-10-20 Created: 2022-10-20 Last updated: 2023-11-20Bibliographically approved
3. Modelling Grice's Maxim of Quantity as Informativeness for Short Text
Open this publication in new window or tab >>Modelling Grice's Maxim of Quantity as Informativeness for Short Text
2020 (English)Conference paper, Published paper (Other academic)
Abstract [en]

Grice's Cooperative Principle (CP) is one of the early theories about good communication. We propose a novel formalisation of one of the sub-components of CP, namely the maxim of quantity (MoQ). We interpret MoQ as informativeness and assume it has an intrinsic relationship to syntactic cohesion. Cohesion establishes a syntactic relationship between elements in a segment of text, and is modelled using syntactic dependency relations between words of the segment.A corpora of 1600 navigation instructions provide the setting for the two proposed metrics: syntactic cohesion for every single segment, and informativeness over all the segments of an instruction. Using a human-subject survey, the metric is evaluated qualitatively and quantitatively. Evaluation results are promising and show a close relationship between the proposed metric scores and the ratings of the participants. Overall, our work indicates that the informativeness of instructions can be captured using a simple syntactic measure.

Keywords
Cooperative Principle, Maxim of Quantity, Dependency Parsing, Syntactic Cohesion, Informativeness, Short Text, Navigation Instructions, Sentences
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
computational linguistics
Identifiers
urn:nbn:se:umu:diva-176269 (URN)
Conference
ICLLL 2020 : The 10th International Conference in Languages, Literature, and Linguistics, Japan, November 6-8, 2020
Funder
EU, Horizon 2020, 721619
Available from: 2020-10-27 Created: 2020-10-27 Last updated: 2023-11-20Bibliographically approved
4. Variational Autoencoding Dialogue Sub-structures Using a Novel Hierarchical Annotation Schema
Open this publication in new window or tab >>Variational Autoencoding Dialogue Sub-structures Using a Novel Hierarchical Annotation Schema
2020 (English)In: 2020 6th IEEE Congress on Information Science and Technology (CiSt) / [ed] Mohammed El Mohajir; Mohammed Al Achhab; Badr Eddine El Mohajir; Bernadetta Kwintiana Ane; Ismail Jellouli, Institute of Electrical and Electronics Engineers (IEEE), 2020, p. 334-341Conference paper, Published paper (Refereed)
Abstract [en]

This work presents a novel method to extract sub-structures in dialogues for the following genres: human-human task driven, human-human chit-chat, human-machine task driven, and human-machine chit-chat dialogues. The model consists of a novel semi-supervised annotation schema of syntactic features, communicative functions, dialogue policy, sequence expansion and sender information. These labels are then transformed into tuples of three, four and five segments, the tuples are used as features and modelled to learn sub-structures in above mentioned genres of dialogues with sequence-to-sequence variational autoencoders. The results analyse the latent space of generic sub-structures decomposed by PCA and ICA, showing an increase in silhouette scores for clustering of the latent space.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2020
Series
Colloquium in Information Science and Technology, CIST, ISSN 2327-185X, E-ISSN 2327-1884
Keywords
Variational autoencoders, Attention Layer, Dialogue sub-structures, Conversation Analysis, Dialogue control functions, Dialogue Policies, LSTM, Hierarchical Agglomerative Clustering, PCA, t-SNE, ICA, sequence expansion
National Category
Computer Systems
Research subject
Computer Science; Linguistics
Identifiers
urn:nbn:se:umu:diva-175254 (URN)10.1109/CiSt49399.2021.9357245 (DOI)000657322100057 ()2-s2.0-85103842753 (Scopus ID)9781728166476 (ISBN)9781728166469 (ISBN)
Conference
4th IEEE Conference on Machine Learning and Natural Language Processing at 6th IEEE Congress on Information Science and Technology, Agadir - Essaouira, Morocco, 5-12 June 2021
Funder
EU, Horizon 2020, 721619
Available from: 2020-09-23 Created: 2020-10-12 Last updated: 2023-11-20Bibliographically approved
5. Forming We-intentions under breakdown situations in human-robot interactions
Open this publication in new window or tab >>Forming We-intentions under breakdown situations in human-robot interactions
2023 (English)In: Computer Methods and Programs in Biomedicine, ISSN 0169-2607, E-ISSN 1872-7565, Vol. 242, article id 107817Article in journal (Refereed) Published
Abstract [en]

Background and Objective: When agents (e.g. a person and a social robot) perform a joint activity to achieve a joint goal, they require sharing a relevant group intention, which has been defined as a We-intention. In forming We-intentions, breakdown situations due to conflicts between internal and “external” intentions are unavoidable, particularly in healthcare scenarios. To study such We-intention formation and “reparation” of conflicts, this paper has a two-fold objective: introduce a general computational mechanism allowing We-intention formation and reparation in interactions between a social robot and a person; and exemplify how the formal framework can be applied to facilitate interaction between a person and a social robot for healthcare scenarios.

Method: The formal computational framework for managing We-intentions was defined in terms of Answer set programming and a Belief-Desire-Intention control loop. We exemplify the formal framework based on earlier theory-based user studies consisting of human-robot dialogue scenarios conducted in a Wizard of Oz setup, video-recorded and evaluated with 20 participants. Data was collected through semi-structured interviews, which were analyzed qualitatively using thematic analysis. N=20 participants (women n=12, men=8, age range 23-72) were part of the study. Two age groups were established for the analysis: younger participants (ages 23-40) and older participants (ages 41-72).

Results: We proved four theoretical propositions, which are well-desired characteristics of any rational social robot. In our study, most participants suggested that people were the cause of breakdown situations. Over half of the young participants perceived the social robot's avoidant behavior in the scenarios.

Conclusions: This work covered in depth the challenge of aligning the intentions of two agents (for example, in a person-robot interaction) when they try to achieve a joint goal. Our framework provides a novel formalization of the We-intentions theory from social science. The framework is supported by formal properties proving that our computational mechanism generates consistent potential plans. At the same time, the agent can handle incomplete and inconsistent intentions shared by another agent (for example, a person). Finally, our qualitative results suggested that this approach could provide an acceptable level of action/intention agreement generation and reparation from a person-centric perspective.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
We-intentions, Breakdown situations, Conflict of intentions, Repairing conflicts, Human-robot interaction, Answer set programming, Logic programming, Shared intentions, Social robots, Healthcare scenarios
National Category
Robotics
Research subject
human-computer interaction
Identifiers
urn:nbn:se:umu:diva-214338 (URN)10.1016/j.cmpb.2023.107817 (DOI)001091730800001 ()37813056 (PubMedID)2-s2.0-851732569172-s2.0-85173256917 (Scopus ID)
Funder
EU, Horizon 2020, 952026
Note

Originally included in thesis in manuscript form.

Available from: 2023-09-12 Created: 2023-09-12 Last updated: 2024-03-13Bibliographically approved
6. Towards we-intentional human-robot interaction using theory of mind and hierarchical task network
Open this publication in new window or tab >>Towards we-intentional human-robot interaction using theory of mind and hierarchical task network
2021 (English)In: Proceedings of the 5th International Conference on Computer-Human Interaction Research and Applications - Volume 1: Humanoid / [ed] Hugo Plácido Silva, Larry Constantine, Andreas Holzinger, Sitepress Digital Library , 2021, p. 291-299Conference paper, Published paper (Refereed)
Abstract [en]

Joint activity between human and robot agent requires them to not only form joint intention and share a mutual understanding about it but also to determine their type of commitment. Such commitment types allows robot agent to select appropriate strategies based on what can be expected from others involved in performing the given joint activity. This work proposes an architecture embedding commitments as we-intentional modes in a belief-desire-intention (BDI) based Theory of Mind (ToM) model. Dialogue mediation gathers observations facilitating ToM to infer the joint activity and hierarchical task network (HTN) plans the execution.The work is ongoing and currently the proposed architecture is being implemented to be evaluated during human-robot interaction studies.

Place, publisher, year, edition, pages
Sitepress Digital Library, 2021
Keywords
We-intention, Joint Intention, Joint Activity, Human-Robot Interaction, We-mode, I-mode, Hierarchical Task Network, Dialogue Interaction
National Category
Robotics
Research subject
human-computer interaction
Identifiers
urn:nbn:se:umu:diva-188969 (URN)10.5220/0010722200003060 (DOI)000796479400030 ()2-s2.0-85146197180 (Scopus ID)978-989-758-538-8 (ISBN)
Conference
The 5th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2021), Online, October 28-29, 2021.
Funder
EU, Horizon 2020, 952026
Note

Special Session on Interaction with Humanoid Robots

Available from: 2021-11-04 Created: 2021-11-04 Last updated: 2023-11-20Bibliographically approved

Open Access in DiVA

spikblad(95 kB)38 downloads
File information
File name SPIKBLAD01.pdfFile size 95 kBChecksum SHA-512
eed03e4a0128e8deac171d687b7fd2e492e4f7cdc34310388dd12162589f31d6b466f520207f6b9c66bc4fdee54a6192e41b36772541765a5ada1c7d282c7717
Type spikbladMimetype application/pdf
fulltext(1546 kB)148 downloads
File information
File name FULLTEXT01.pdfFile size 1546 kBChecksum SHA-512
80acd27e6753b742dfca729290ee0a9aacf1d5e7687e770e099ffafb4f9157eb62c26330fb7df9dbf8a787f9cb2f5669316cb345294fa78c59ac72f62b8b637d
Type fulltextMimetype application/pdf

Authority records

Tewari, Maitreyee

Search in DiVA

By author/editor
Tewari, Maitreyee
By organisation
Department of Computing Science
Human Computer InteractionLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 148 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1211 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf