scholarly journals Cutting melted butter? Common Ground inconsistencies management in dialogue systems using graph databases

2021 ◽  
Vol 7 (1 | 2) ◽  
pp. 157-190
Author(s):  
Maria Di Maro ◽  
Antonio Origlia ◽  
Francesco Cutugno
Keyword(s):  
Common Ground ◽  
Graph Databases ◽  
Dialogue Systems

scholarly journals Maintaining Common Ground in Dynamic Environments

2021 ◽  
Vol 9 ◽  
pp. 995-1011
Author(s):  
Takuma Udagawa ◽  
Akiko Aizawa
Keyword(s):  
Large Scale ◽  
Common Ground ◽  
Dynamic Environments ◽  
Dialogue Systems ◽  
Human Communication ◽  
Dialogue System ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Temporal Expressions ◽  
Spatio Temporal

Abstract Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication. While various task settings have been proposed in existing literature, they mostly focus on creating common ground under a static context and ignore the aspect of maintaining them overtime under dynamic context. In this work, we propose a novel task setting to study the ability of both creating and maintaining common ground in dynamic environments. Based on our minimal task formulation, we collected a large-scale dataset of 5,617 dialogues to enable fine-grained evaluation and analysis of various dialogue systems. Through our dataset analyses, we highlight novel challenges introduced in our setting, such as the usage of complex spatio-temporal expressions to create and maintain common ground. Finally, we conduct extensive experiments to assess the capabilities of our baseline dialogue system and discuss future prospects of our research.

scholarly journals Common Ground, Frames and Slots for Comprehension in Dialogue Systems

2021 ◽  
Author(s):  
Philippe Blache ◽  
Matthis Houlès
Keyword(s):  
Natural Language ◽  
Common Ground ◽  
Bad News ◽  
Shared Knowledge ◽  
Dialogue Systems ◽  
Dialogue System ◽  
Language Understanding ◽  
Language Generation ◽  
The Universe ◽  
Universe Of Discourse

This paper presents a dialogue system for training doctors to break bad news. The originality of this work lies in its knowledge representation. All information known before the dialogue (the universe of discourse, the context, the scenario of the dialogue) as well as the knowledge transferred from the doctor to the patient during the conversation is represented in a shared knowledge structure called common ground, that constitute the core of the system. The Natural Language Understanding and the Natural Language Generation modules of the system take advantage on this structure and we present in this paper different original techniques making it possible to implement them efficiently.

scholarly journals A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context

2019 ◽  
Vol 33 ◽  
pp. 7120-7127
Author(s):  
Takuma Udagawa ◽  
Akiko Aizawa
Keyword(s):  
Natural Language ◽  
Common Ground ◽  
Dialogue Systems ◽  
Human Communication ◽  
Neural Models ◽  
Critical Aspect ◽  
Complex Models ◽  
Partially Observable ◽  
Language Corpus ◽  
Advanced Skills

Common grounding is the process of creating, repairing and updating mutual understandings, which is a critical aspect of sophisticated human communication. However, traditional dialogue systems have limited capability of establishing common ground, and we also lack task formulations which introduce natural difficulty in terms of common grounding while enabling easy evaluation and analysis of complex models. In this paper, we propose a minimal dialogue task which requires advanced skills of common grounding under continuous and partially-observable context. Based on this task formulation, we collected a largescale dataset of 6,760 dialogues which fulfills essential requirements of natural language corpora. Our analysis of the dataset revealed important phenomena related to common grounding that need to be considered. Finally, we evaluate and analyze baseline neural models on a simple subtask that requires recognition of the created common ground. We show that simple baseline models perform decently but leave room for further improvement. Overall, we show that our proposed task will be a fundamental testbed where we can train, evaluate, and analyze dialogue system’s ability for sophisticated common grounding.

Talking Across Cultures in Early Intervention: Finding Common Ground to Meet Children's Communication Needs

2009 ◽  
Vol 16 (3) ◽  
pp. 79-85 ◽  
Author(s):  
Elizabeth D. Peña ◽  
Christine Fiestas
Keyword(s):  
Early Intervention ◽  
Cultural Values ◽  
Common Ground ◽  
Service Providers ◽  
Cultural Orientation ◽  
Speech Language Pathology ◽  
Provider Perspectives ◽  
Language Pathology ◽  
Communication Needs ◽  
Caregiver Role

Abstract In this paper, we explore cultural values and expectations that might vary among different groups. Using the collectivist-individualist framework, we discuss differences in beliefs about the caregiver role in teaching and interacting with young children. Differences in these beliefs can lead to dissatisfaction with services on the part of caregivers and with frustration in service delivery on the part of service providers. We propose that variation in caregiver and service provider perspectives arise from cultural values, some of which are instilled through our own training as speech-language pathologists. Understanding where these differences in cultural orientation originate can help to bridge these differences. These can lead to positive adaptations in the ways that speech-language pathology services are provided within an early intervention setting that will contribute to effective intervention.

Spatial Representations as an Emergent Feature of Perceptual Processing

2010 ◽  
Vol 24 (3) ◽  
pp. 161-172 ◽  
Author(s):  
Edmund Wascher ◽  
C. Beste
Keyword(s):  
Common Ground ◽  
Event Related Potentials ◽  
Vertical Axis ◽  
Relevant Information ◽  
Sources Of Information ◽  
Integrated Network ◽  
Perceptual Maps ◽  
Emergent Feature ◽  
Related Potentials ◽  
Selection Of

Spatial selection of relevant information has been proposed to reflect an emergent feature of stimulus processing within an integrated network of perceptual areas. Stimulus-based and intention-based sources of information might converge in a common stage when spatial maps are generated. This approach appears to be inconsistent with the assumption of distinct mechanisms for stimulus-driven and top-down controlled attention. In two experiments, the common ground of stimulus-driven and intention-based attention was tested by means of event-related potentials (ERPs) in the human EEG. In both experiments, the processing of a single transient was compared to the selection of a physically comparable stimulus among distractors. While single transients evoked a spatially sensitive N1, the extraction of relevant information out of a more complex display was reflected in an N2pc. The high similarity of the spatial portion of these two components (Experiment 1), and the replication of this finding for the vertical axis (Experiment 2) indicate that these two ERP components might both reflect the spatial representation of relevant information as derived from the organization of perceptual maps, just at different points in time.

Sign in / Sign up

Export Citation Format

Share Document