pith. sign in

arxiv: 1907.00684 · v1 · pith:HJ76J246new · submitted 2019-07-01 · 💻 cs.HC

Enabling Dialogue Management with Dynamically Created Dialogue Actions

Juliana Miehle , Louisa Pragst , Wolfgang Minker , Stefan Ultes This is my paper

Pith reviewed 2026-05-25 11:45 UTC · model grok-4.3

classification 💻 cs.HC
keywords dialogue managementdynamic actionsuser adaptationspoken dialogue systemsflexibilityevaluation
0
0 comments X

The pith

Extending a dialogue manager to create actions dynamically increases flexibility for adapting spoken systems to individual users.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper describes modifications to an existing dialogue manager so that it can generate and manage dialogue actions during a conversation rather than relying only on a fixed set prepared in advance. This change is presented as a way to support user-adaptive behavior by allowing the system to respond more flexibly to what the user does. The authors integrated the updated manager into a complete spoken dialogue system and tested it with human participants. The evaluation showed that people held meaningful exchanges and the system operated without major problems.

Core claim

The central claim is that the implemented modifications enable the dialogue manager to handle dynamically created dialogue actions, thereby increasing flexibility that can be used for adaptation tasks, and that integration into a full spoken dialogue system permits participants to conduct meaningful dialogues while the system performs satisfactorily.

What carries the argument

The extension that lets the dialogue manager create and process dialogue actions on the fly instead of using only predefined ones.

If this is right

  • The added flexibility can be applied to adaptation tasks during live conversations.
  • Users remain able to hold coherent and meaningful dialogues with the integrated system.
  • The dialogue manager operates at a satisfactory level once placed inside a full spoken dialogue system.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Dynamic action creation could let systems adjust response style or content based on detected user knowledge or preference without requiring every possible path to be written beforehand.
  • The approach might be combined with user modeling components to decide which new actions to generate at each turn.
  • Scalability questions arise when the number of on-the-fly actions grows large in longer or multi-domain conversations.

Load-bearing premise

The participant evaluation is sufficient to show that dynamic action handling succeeds at enabling user-adaptive behavior, even though the specific adaptation tasks and measurement criteria are not described.

What would settle it

A controlled test in which the system must change its dialogue strategy in response to user-specific input and either succeeds or fails to maintain coherence when actions are generated dynamically.

read the original abstract

In order to take up the challenge of realising user-adaptive system behaviour, we present an extension for the existing OwlSpeak Dialogue Manager which enables the handling of dynamically created dialogue actions. This leads to an increase in flexibility which can be used for adaptation tasks. After the implementation of the modifications and the integration of the Dialogue Manager into a full Spoken Dialogue System, an evaluation of the system has been carried out. The results indicate that the participants were able to conduct meaningful dialogues and that the system performs satisfactorily, showing that the implementation of the Dialogue Manager was successful.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents an extension to the OwlSpeak Dialogue Manager enabling the handling of dynamically created dialogue actions to increase flexibility for user-adaptive behavior in spoken dialogue systems. It describes the implementation of these modifications, integration into a full Spoken Dialogue System, and reports results from a user evaluation indicating that participants conducted meaningful dialogues and rated the system satisfactorily, concluding that the Dialogue Manager implementation was successful.

Significance. The core idea of supporting dynamic dialogue actions to enable adaptation is relevant to dialogue management research. If the evaluation had included targeted metrics isolating the dynamic mechanism's contribution (e.g., adaptation task success, dynamic action counts, baseline comparisons), the work could provide a concrete demonstration of increased flexibility; as presented, the significance is limited to a general usability report without attribution to the claimed extension.

major comments (2)
  1. [Evaluation section] Evaluation section: The reported results state only that 'participants were able to conduct meaningful dialogues and that the system performs satisfactorily' without any adaptation-specific tasks, quantitative metrics on dynamic action instantiation or usage, task success rates under changing user goals, or comparison against the static OwlSpeak baseline. This prevents attribution of the observed usability to the dynamic-action extension and undermines the central claim that the modification enables user-adaptive behavior.
  2. [Implementation section] Implementation description (likely §3): The manuscript provides no concrete details on the mechanism for creating and managing dynamic actions (e.g., data structures, triggering conditions, or integration points with the existing OwlSpeak state machine), making it impossible to assess correctness, reproducibility, or novelty of the extension.
minor comments (1)
  1. [Abstract] The abstract lacks any mention of participant numbers, evaluation metrics, or adaptation scenarios, which reduces clarity for readers seeking to understand the scope of the claimed success.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below and agree that the manuscript would benefit from additional detail and metrics. Revisions will be made accordingly.

read point-by-point responses

  1. Referee: [Evaluation section] Evaluation section: The reported results state only that 'participants were able to conduct meaningful dialogues and that the system performs satisfactorily' without any adaptation-specific tasks, quantitative metrics on dynamic action instantiation or usage, task success rates under changing user goals, or comparison against the static OwlSpeak baseline. This prevents attribution of the observed usability to the dynamic-action extension and undermines the central claim that the modification enables user-adaptive behavior.

    Authors: The evaluation was intended as an initial demonstration that the extended dialogue manager could be integrated into a full SDS and support coherent user interactions. We acknowledge that it does not isolate the contribution of dynamic actions via baseline comparison or adaptation-specific metrics. In revision we will add quantitative counts of dynamic action instantiation and usage, plus a discussion of how these supported observed dialogue flexibility. revision: yes

  2. Referee: [Implementation section] Implementation description (likely §3): The manuscript provides no concrete details on the mechanism for creating and managing dynamic actions (e.g., data structures, triggering conditions, or integration points with the existing OwlSpeak state machine), making it impossible to assess correctness, reproducibility, or novelty of the extension.

    Authors: The current description of the extension is at a conceptual level. We agree that concrete implementation details are needed for reproducibility. The revised manuscript will expand the relevant section with descriptions of the data structures for dynamic actions, the triggering conditions, and the integration points within the OwlSpeak state machine. revision: yes

Circularity Check

0 steps flagged

No circularity: implementation report with direct evaluation

full rationale

The paper presents an engineering extension to an existing dialogue manager (OwlSpeak) plus a user study. No equations, parameters, or derivations are present in the provided text or abstract. The central claim rests on the reported usability results rather than any reduction to fitted inputs, self-definitions, or self-citation chains. No load-bearing step matches any of the enumerated circularity patterns; the evaluation is presented as an independent outcome of the implementation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As an applied implementation paper in dialogue systems, there are no free parameters, mathematical axioms, or invented entities; the work relies on the existing OwlSpeak system as a base.

pith-pipeline@v0.9.0 · 5616 in / 1096 out tokens · 31390 ms · 2026-05-25T11:45:21.506741+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

14 extracted references · 14 canonical work pages · 1 internal anchor

  1. [1]

    Bohus, D., Rudnicky, A.I.: Ravenclaw: Dialog management using hierarchical task decompo- sition and an expectation agenda (2003)

    work page 2003

  2. [2]

    EMA/CHMP/ ICH/135/1995 (2016)

    European Medicines Agency: Guideline for Good Clinical Practice E6(R2). EMA/CHMP/ ICH/135/1995 (2016). Available from: http://www.ich.org/products/guidelines/efficacy/ article/efficacy-guidelines.html. Accessed on: January 11, 2018

    work page 1995

  3. [3]

    In: Pervasive Computing and Communications Workshops (PERCOM Workshops), 2010 8th IEEE International Conference on, pp

    Heinroth, T., Denich, D., Schmitt, A.: OwlSpeak - Adaptive Spoken Dialogue within Intel- ligent Environments. In: Pervasive Computing and Communications Workshops (PERCOM Workshops), 2010 8th IEEE International Conference on, pp. 666–671. IEEE (2010)

    work page 2010

  4. [4]

    In: 10th International Conference on Intelligent Environments (IE 2014), pp

    Honold, F., Bercher, P., Richter, F., Nothdurft, F., Geier, T., Barth, R., Hoernle, T., Sch¨ussel, F., Reuter, S., Rau, M., Bertrand, G., Seegebarth, B., Kurzok, P., Schattenberg, B., Minker, W., Weber, M., Biundo, S.: Companion-technology: Towards user- and situation-adaptive func- tionality of technical systems. In: 10th International Conference on Inte...

    work page 2014

  5. [5]

    In: Proceedings of the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction, pp

    Meditskos, G., Dasiopoulou, S., Pragst, L., Ultes, S., Vrochidis, S., Kompatsiaris, I., Wanner, L.: Towards an ontology-driven adaptive dialogue framework. In: Proceedings of the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction, pp. 15–20. ACM (2016)

    work page 2016

  6. [6]

    In: 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, p

    Miehle, J., Yoshino, K., Pragst, L., Ultes, S., Nakamura, S., Minker, W.: Cultural communi- cation idiosyncrasies in human-computer interaction. In: 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, p. 74 (2016)

    work page 2016

  7. [7]

    In: SIG- DIAL Conference, pp

    Nothdurft, F., Richter, F., Minker, W.: Probabilistic human-computer trust handling. In: SIG- DIAL Conference, pp. 51–59 (2014)

    work page 2014

  8. [8]

    LD-SDS: Towards an Expressive Spoken Dialogue System based on Linked-Data

    Papangelis, A., Papadakos, P., Kotti, M., Stylianou, Y ., Tzitzikas, Y ., Plexousakis, D.: Ld- sds: Towards an expressive spoken dialogue system based on linked-data. arXiv preprint arXiv:1710.02973 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  9. [9]

    Taligent Inc p

    Potel, M.: Mvp: Model-view-presenter the taligent programming model for c++ and java. Taligent Inc p. 20 (1996)

    work page 1996

  10. [10]

    In: Proceedings of the 8th International Workshop On Spoken Dialogue Systems (IWSDS) (2017)

    Pragst, L., Minker, W., Ultes, S.: Exploring the applicability of elaborateness and indirect- ness in dialogue management. In: Proceedings of the 8th International Workshop On Spoken Dialogue Systems (IWSDS) (2017)

    work page 2017

  11. [11]

    Proceedings of the 19thWorkshop on the Semantics and Pragmatics of Dialogue (SEMDIAL) pp

    Pragst, L., Ultes, S., Kraus, M., Minker, W.: Adaptive dialogue management in the kristina project for multicultural health care applications. Proceedings of the 19thWorkshop on the Semantics and Pragmatics of Dialogue (SEMDIAL) pp. 202–203 (2015)

    work page 2015

  12. [12]

    In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp

    Ultes, S., Kraus, M., Schmitt, A., Minker, W.: Quality-adaptive spoken dialogue initiative selection and implications on reward modelling. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 374–383 (2015)

    work page 2015

  13. [13]

    Jour- nal of Ambient Intelligence and Smart Environments 6(5), 523–539 (2014)

    Ultes, S., Minker, W.: Managing adaptive spoken dialogue for intelligent environments. Jour- nal of Ambient Intelligence and Smart Environments 6(5), 523–539 (2014)

    work page 2014

  14. [14]

    In: Proceedings of the 15th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS’17) (2017)

    Wanner, L., Andr ´e, E., Blat, J., Dasiopoulou, S., Farr ´us, M., Fraga, T., Kamateri, E., Lingen- felser, F., Llorach, G., Martinez, O., Meditskos, G., Mille, S., Minker, W., Pragst, L., Schiller, D., Stam, A., Stellingwerff, L., Sukno, F., Vieru, B., Vrochidis, S.: Kristina: A knowledge- based virtual conversation agent. In: Proceedings of the 15th Inte...

    work page 2017