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 ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

2021 ◽  
Author(s):  
Anil S. Baslamisli ◽  
Partha Das ◽  
Hoang-An Le ◽  
Sezer Karaoglu ◽  
Theo Gevers
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
State Of The Art ◽  
Image Decomposition ◽  
Natural Environments ◽  
Decomposition Algorithms ◽  
Ambient Light ◽  
Fine Grained ◽  
Large Scale Dataset ◽  
Direct Illumination

AbstractIn general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in distinguishing strong photometric effects from reflectance variations. Therefore, in this paper, we propose to decompose the shading component into direct (illumination) and indirect shading (ambient light and shadows) subcomponents. The aim is to distinguish strong photometric effects from reflectance variations. An end-to-end deep convolutional neural network (ShadingNet) is proposed that operates in a fine-to-coarse manner with a specialized fusion and refinement unit exploiting the fine-grained shading model. It is designed to learn specific reflectance cues separated from specific photometric effects to analyze the disentanglement capability. A large-scale dataset of scene-level synthetic images of outdoor natural environments is provided with fine-grained intrinsic image ground-truths. Large scale experiments show that our approach using fine-grained shading decompositions outperforms state-of-the-art algorithms utilizing unified shading on NED, MPI Sintel, GTA V, IIW, MIT Intrinsic Images, 3DRMS and SRD datasets.

CSMC

2021 ◽  
Vol 5 (4) ◽  
pp. 1-22
Author(s):  
Hai Wang ◽  
Baoshen Guo ◽  
Shuai Wang ◽  
Tian He ◽  
Desheng Zhang
Keyword(s):  
Large Scale ◽  
Mobile Network ◽  
Signal Propagation ◽  
Spectrum Management ◽  
External Information ◽  
Temporal Uncertainty ◽  
Large Area ◽  
Fine Grained ◽  
Map Construction ◽  
Spatio Temporal

The rise concern about mobile communication performance has driven the growing demand for the construction of mobile network signal maps which are widely utilized in network monitoring, spectrum management, and indoor/outdoor localization. Existing studies such as time-consuming and labor-intensive site surveys are difficult to maintain an update-to-date finegrained signal map within a large area. The mobile crowdsensing (MCS) paradigm is a promising approach for building signal maps because collecting large-scale MCS data is low-cost and with little extra-efforts. However, the dynamic environment and the mobility of the crowd cause spatio-temporal uncertainty and sparsity of MCS. In this work, we leverage MCS as an opportunity to conduct the city-wide mobile network signal map construction. We propose a fine-grained city-wide Cellular Signal Map Construction (CSMC) framework to address two challenges including (i) the problem of missing and unreliable MCS data; (ii) spatio-temporal uncertainty of signal propagation. In particular, CSMC captures spatio-temporal characteristics of signals from both inter- and intra- cellular base stations and conducts missing signal recovery with Bayesian tensor decomposition to build large-area fine-grained signal maps. Furthermore, CSMC develops a context-aware multi-view fusion network to make full use of external information and enhance signal map construction accuracy. To evaluate the performance of CSMC, we conduct extensive experiments and ablation studies on a large-scale dataset with over 200GB MCS signal records collected from Shanghai. Experimental results demonstrate that our model outperforms state-of-the-art baselines in the accuracy of signal estimation and user localization.

scholarly journals MODELLING OF COLLECTIVE MOVEMENT IN IMMERSIVE ENVIRONMENTS

2018 ◽  
Vol XLII-4 ◽  
pp. 397-402 ◽  
Author(s):  
G. Magallanes Guijón ◽  
F. Hruby ◽  
R. Ressl ◽  
V. Aguilar Sierra ◽  
G. de la Borbolla del Valle ◽  
...  
Keyword(s):  
Large Scale ◽  
Physical Reality ◽  
Spatial Presence ◽  
Collective Movement ◽  
Fine Grained ◽  
Immersive Virtual Environment ◽  
Viable Solution ◽  
Self Organized Criticality ◽  
Spatio Temporal ◽  
Basic Characteristics

<p><strong>Abstract.</strong> Immersive technologies allow us to map physical reality by means of 4D virtual systems in ever higher spatial and temporal detail, up to a scale level of 1<span class="thinspace"></span>:<span class="thinspace"></span>1. This level of detail enables the representation of phenomena that have been widely ignored by the geovisualization research agenda as yet. An example for such a large scale phenomenon is the collective movement of animals, which can be modelled and visualized only at a fine grained spatio-temporal resolution. This paper focuses on how collective movement can be modelled in an immersive virtual reality (VR) geovisualization. In a brief introduction on immersion and spatial presence we will argue, that high fidelity and realistic VR can strengthen the users’ involvement with the issues visualized. We will then discuss basic characteristics of swarming in nature and review the principal models that have been presented to formalize this collective behavior. Based on the rules of (1) collision avoidance, (2) polarization, (3) aggregation and (4) self-organized criticality we will formulate a viable solution of modelling collective movement within a geovisualization immersive virtual environment. An example of use and results will be presented.</p>

scholarly journals Dissociable effects of prediction and integration during language comprehension: evidence from a large-scale study using brain potentials

2019 ◽  
Vol 375 (1791) ◽  
pp. 20180522 ◽  
Author(s):  
Mante S. Nieuwland ◽  
Dale J. Barr ◽  
Federica Bartolozzi ◽  
Simon Busch-Moreno ◽  
Emily Darley ◽  
...  
Keyword(s):  
Semantic Processing ◽  
Large Scale ◽  
Word Meaning ◽  
Mixed Effect ◽  
Fine Grained ◽  
Sentence Level ◽  
Spatio Temporal ◽  
Word Predictability ◽  
Using Data ◽  
Temporal Profiles

Composing sentence meaning is easier for predictable words than for unpredictable words. Are predictable words genuinely predicted, or simply more plausible and therefore easier to integrate with sentence context? We addressed this persistent and fundamental question using data from a recent, large-scale ( n = 334) replication study, by investigating the effects of word predictability and sentence plausibility on the N400, the brain's electrophysiological index of semantic processing. A spatio-temporally fine-grained mixed-effect multiple regression analysis revealed overlapping effects of predictability and plausibility on the N400, albeit with distinct spatio-temporal profiles. Our results challenge the view that the predictability-dependent N400 reflects the effects of either prediction or integration, and suggest that semantic facilitation of predictable words arises from a cascade of processes that activate and integrate word meaning with context into a sentence-level meaning. This article is part of the theme issue ‘Towards mechanistic models of meaning composition’.

scholarly journals A TENSOR BASED FRAMEWORK FOR LARGE SCALE SPATIO-TEMPORAL RASTER DATA PROCESSING

2019 ◽  
Vol XLII-4/W14 ◽  
pp. 3-9
Author(s):  
S. Bhattacharya ◽  
C. Braun ◽  
U. Leopold
Keyword(s):  
Large Scale ◽  
Solar Irradiation ◽  
Raster Data ◽  
Fine Grained ◽  
Multiple Dimensions ◽  
Proposed Model ◽  
Spatio Temporal ◽  
Using Data ◽  
Tensor Data ◽  
Flow Graphs

Abstract. In this paper, we address the curse of dimensionality and scalability issues while managing vast volumes of multidimensional raster data in the renewable energy modeling process in an appropriate spatial and temporal context. Tensor representation provides a convenient way to capture inter-dependencies along multiple dimensions. In this direction, we propose a sophisticated way of handling large-scale multi-layered spatio-temporal data, adopted for raster-based geographic information systems (GIS). We chose Tensorflow, an open source software library developed by Google using data flow graphs, and the tensor data structure. We provide a comprehensive performance evaluation of the proposed model against r.sun in GRASS GIS. Benchmarking shows that the tensor-based approach outperforms by up to 60%, concerning overall execution time for high-resolution datasets and fine-grained time intervals for daily sums of solar irradiation [Wh.m-2.day-1].

scholarly journals More to diverse: Generating diversified responses in a task oriented multimodal dialog system

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0241271
Author(s):  
Mauajama Firdaus ◽  
Arunav Pratap Shandeelya ◽  
Asif Ekbal
Keyword(s):  
Large Scale ◽  
Contextual Information ◽  
Empirical Evaluation ◽  
Dialogue Systems ◽  
Beam Search ◽  
Dialogue System ◽  
Text And Image ◽  
Dialog System ◽  
Multimodal Dialogue ◽  
Task Oriented

Multimodal dialogue system, due to its many-fold applications, has gained much attention to the researchers and developers in recent times. With the release of large-scale multimodal dialog dataset Saha et al. 2018 on the fashion domain, it has been possible to investigate the dialogue systems having both textual and visual modalities. Response generation is an essential aspect of every dialogue system, and making the responses diverse is an important problem. For any goal-oriented conversational agent, the system’s responses must be informative, diverse and polite, that may lead to better user experiences. In this paper, we propose an end-to-end neural framework for generating varied responses in a multimodal dialogue setup capturing information from both the text and image. Multimodal encoder with co-attention between the text and image is used for focusing on the different modalities to obtain better contextual information. For effective information sharing across the modalities, we combine the information of text and images using the BLOCK fusion technique that helps in learning an improved multimodal representation. We employ stochastic beam search with Gumble Top K-tricks to achieve diversified responses while preserving the content and politeness in the responses. Experimental results show that our proposed approach performs significantly better compared to the existing and baseline methods in terms of distinct metrics, and thereby generates more diverse responses that are informative, interesting and polite without any loss of information. Empirical evaluation also reveals that images, while used along with the text, improve the efficiency of the model in generating diversified responses.

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.

Sign in / Sign up

Export Citation Format

Share Document