Learning Exceptions to Refine a Domain Expertise

2011 ◽  
pp. 1129-1136
Author(s):  
Rallou Thomopoulos
Keyword(s):  
Experimental Data ◽  
Graphical Representation ◽  
Rule Learning ◽  
Graph Model ◽  
Relational Model ◽  
Generic Level ◽  
Domain Experts ◽  
Conceptual Graph ◽  
Domain Expertise ◽  
Numerous Data

This chapter deals with the problem of the cooperation of heterogeneous knowledge for the construction of a domain expertise, and more specifically for the discovery of new unexpected knowledge. Two kinds of knowledge are taken into account: • Expert statements. They constitute generic knowledge which rises from the experience of domain experts and describes commonly admitted mechanisms that govern the domain. This knowledge is represented as conceptual graph rules, which has the advantage to combine a logic-based formalism and an equivalent graphical representation, essential for non-specialist users (Bos, 1997). • Experimental data, given by international literature of the domain. They are represented in the relational model. These numerous data describe in detail, in a quantitative way, experiments that were carried out to deepen the knowledge of the domain, and the obtained results. These results may confirm the knowledge provided by the expert statements – or not. The cooperation of both kinds of knowledge aims, firstly, at testing the validity of the expert statements within the experimental data, secondly, at discovering refinements of the expert statements to consolidate the domain expertise. Two major differences between the two formalisms are the following. Firstly, the conceptual graphs represent knowledge at a more generic level than the relational data. Secondly, the conceptual graph model includes an ontological part (hierarchized vocabulary that constitutes the support of the model), contrary to the relational model. We introduce a process that allows one to test the validity of expert statements within the experimental data, that is, to achieve the querying of a relational database by a system expressed in the conceptual graph formalism. This process is based on the use of annotated conceptual graph patterns. When an expert statement appears not to be valid, a second-step objective is to refine it. This refinement consists of an automatic exception rule learning which provides unexpected knowledge in regard of previously established knowledge. The examples given in this chapter have been designed using the CoGui tool (http://www.lirmm. fr/cogui/) and concern a concrete application in the domain of food quality.

Knowledge Transfer for Entity Resolution with Siamese Neural Networks

2021 ◽  
Vol 13 (1) ◽  
pp. 1-25
Author(s):  
Michael Loster ◽  
Ioannis Koumarelas ◽  
Felix Naumann
Keyword(s):  
Knowledge Transfer ◽  
Similarity Measure ◽  
State Of The Art ◽  
Similarity Measures ◽  
Engineering Process ◽  
Domain Experts ◽  
Multiple Datasets ◽  
Multiple Data ◽  
Domain Expertise ◽  
F Measure

The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity—duplicates—into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise. We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.

A theoretical study of adiabatic proton transfer to simple substituted acetylenes In Their Ground And Excited States

1989 ◽  
Vol 67 (12) ◽  
pp. 2178-2187 ◽  
Author(s):  
Peter S. Martin ◽  
Keith Yates ◽  
Imre G. Csizmadia
Keyword(s):  
Experimental Data ◽  
Proton Transfer ◽  
Excited States ◽  
Graphical Representation ◽  
Proton Affinities ◽  
Energy Profiles ◽  
Singlet States ◽  
Vinyl Cation ◽  
Substituted Acetylenes ◽  
Ordered Pairs

RHF SCF 3-21G calculations are reported for the 1Σg+, 1A1, 3A′, and 1,3A″ states of simple substituted acetylenes (Y—C≡C—H, where Y = H, F, Cl,CH3, andCF3), the 1A1, 1A′, and 1.3A″ states of their Markovnikov (M) vinyl cations (Y—C+ = CH2), the 1A′ and 1.3A″ states of their anti-Markovnikov (aM) vinyl cations (YCH=C+H), and the corresponding hydrated vinyl cations. Equilibrium electronic structures and the mechanism of adiabatic protonation are described qualitatively via Lewis/resonance schematic representations of the species involved. Calculated proton affinities (PA) suggest that relative to ground state Y—C≡C—H (1Σ+/1A1), Y—C≡C—H* (1.3A″) is of greatly enhanced basicity with respect to protonation of both regiocenters. A graphical representation of the ordered pairs PA(M) versus PA(aM) as a function of substituent Y and electronic state, leads to the conclusions: (1) irrespective of both regiocenter (M/aM) and state (1Σ1+/1A1, 3A, 1.3A″) the PA's for Y—C≡C—H decrease in the order CH3 > H > Cl> F > CF3; (2) in proceeding from CH3C≡CH to CF3C≡CH, a change in protonation regiospecificity (M → aM) is experienced to approximately the same extent for both S0 and S1; (3) T2 exhibits no significant protonation regioselectivity. Critical comparison of the calculated results is made with available experimental data. An approximate picture of the energy profiles for the adiabatic hydrations of Y—C≡C—H via its ground, triplet and singlet states has been developed, based on the fixed points acetylene, vinyl cation and hydrated vinyl cation. Predicted relative reactivities of these three states are in excellent accord with available experimental data on rates of hydration. Keywords: excited states, proton transfer, photohydration.

scholarly journals A Measure of the Interference Effect Distribution

2019 ◽  
Author(s):  
thibault gajdos ◽  
Mathieu Servant ◽  
Thierry Hasbroucq ◽  
Karen Davranche
Keyword(s):  
Experimental Data ◽  
Interference Effect ◽  
Graphical Representation ◽  
Response Times ◽  
Cognitive Model ◽  
Individual Data ◽  
Interference Effects ◽  
Distribution Index

We elaborated an index, the Interference Distribution Index, that allows to quantify the relation between response times and the size of the interference effect. This index is associated to an intuitive graphical representation, the Lorenz-interference plot. We show that this index has some convenient properties in terms of sensitivity to changes in the distribution of the interference effect and to aggregation of individual data. Moreover, it turns out that this index is the only one (up to an arbitrary increasing transformation) possessing these properties. The relevance of this index is illustrated through simulations of a cognitive model of interference effects and reanalysis of experimental data.

When the Machine Meets the Expert: An Ethnography of Developing AI for Hiring

MIS Quarterly ◽  
2021 ◽  
Vol 45 (3) ◽  
pp. 1557-1580
Author(s):  
Elmira van den Broek ◽  
◽  
Anastasia Sergeeva ◽  
Marleen Huysman Vrije ◽  
◽  
...  
Keyword(s):  
Information Technologies ◽  
System Development ◽  
Knowledge Work ◽  
Ethnographic Study ◽  
International Organization ◽  
Information System Development ◽  
Domain Experts ◽  
Mutual Learning ◽  
Job Candidates ◽  
Domain Expertise

The introduction of machine learning (ML)in organizations comes with the claim that algorithms will produce insights superior to those of experts by discovering the “truth” from data. Such a claim gives rise to a tension between the need to produce knowledge independent of domain experts and the need to remain relevant to the domain the system serves. This two-year ethnographic study focuses on how developers managed this tension when building an ML system to support the process of hiring job candidates at a large international organization. Despite the initial goal of getting domain experts “out the loop,” we found that developers and experts arrived at a new hybrid practice that relied on a combination of ML and domain expertise. We explain this outcome as resulting from a process of mutual learning in which deep engagement with the technology triggered actors to reflect on how they produced knowledge. These reflections prompted the developers to iterate between excluding domain expertise from the ML system and including it. Contrary to common views that imply an opposition between ML and domain expertise, our study foregrounds their interdependence and as such shows the dialectic nature of developing ML. We discuss the theoretical implications of these findings for the literature on information technologies and knowledge work, information system development and implementation, and human–ML hybrids.

Diagnosing Macroergonomic Problems: A Case Study in the Use of Concept Mapping for TQM Initiatives

1993 ◽  
Vol 37 (12) ◽  
pp. 873-876 ◽  
Author(s):  
Brian S. Zaff ◽  
Edward R. Hughes ◽  
Michael D. McNeese ◽  
Clifford E. Brown ◽  
Maryalice Citera
Keyword(s):  
Knowledge Acquisition ◽  
Concept Mapping ◽  
Graphical Representation ◽  
Team Building ◽  
Mapping Technique ◽  
Total Quality ◽  
Group Setting ◽  
Team Members ◽  
Domain Experts

This paper presents the results from a case study involving the use of concept mapping in a Total Quality Management (TQM) program. Concept mapping is a knowledge acquisition technique that has proven successful in a variety of instances when it was necessary to elicit information directly from domain experts and communicate that information to other individuals needing the information. The concept mapping technique produces, during the course of an interview, a graphical representation that becomes a communications medium through which ideas can be easily shared in a group setting. In TQM programs it may be necessary to elicit detailed information from employees about the nature of their work domain and about the various problems they may be encountering. The success of TQM programs often depends on establishing open lines of communications through which employees can articulate their concerns and upon the ability of TQM team members to uncover hard-to-detect problems. Concept mapping proved successful in the TQM setting. The concept mapping technique facilitated the uncovering of insights that were not obvious to the TQM team during their initial brainstorming sessions or from the use of a survey. In addition it appears that the concept mapping technique has other significant TQM advantages over and above its utility as a knowledge elicitation technique. Concept mapping, not only facilitates user-centered knowledge acquisition, but also appears useful as a means of facilitating team-building.

scholarly journals Manning's roughness coefficient determination in laboratory experiments using 2D modeling and automatic calibration

2020 ◽  
pp. 22-33
Author(s):  
Basile Lavoie ◽  
Tew-Fik Mahdi
Keyword(s):  
Experimental Data ◽  
Laboratory Experiments ◽  
Numerical Models ◽  
Roughness Coefficient ◽  
Automatic Calibration ◽  
Test Cases ◽  
Data Sets ◽  
Step Method ◽  
Numerous Data

Reliable experimental data are essential for choosing and validating numerical models. Although numerous data sets have been presented in the literature, few have been made widely available to the scientific community. Additionally, these experimental data sets have generally given little attention to the determination of Manning's roughness coefficients. This paper addresses these two issues. Three channel configurations are studied: a flatbed channel, a channel with a triangular sill and a channel with a triangular abutment. Three increasing permanent discharges are used for each configuration, leading to nine test cases. The Manning's coefficients are determined using three methods: the traditional step method, automatic calibration, via a 2D hydrodynamic model, considering theoretical value intervals and automatic calibration ignoring these intervals. The results show that automatic calibration with theoretical value intervals is advantageous compared to the step method. Automatic calibration ignoring theoretical intervals yields low errors but unphysical values; therefore, it is not recommended.

Narrative and Conceptual Expertise in Massively Multiplayer Online Role Playing Games

2016 ◽  
Vol 8 (1) ◽  
pp. 44-67 ◽  
Author(s):  
Javier Alejandro Corredor ◽  
Leonardo Rojas Benavides
Keyword(s):  
Role Playing ◽  
World Of Warcraft ◽  
Design Task ◽  
Domain Experts ◽  
Role Playing Games ◽  
Character Design ◽  
Domain Expertise ◽  
Massively Multiplayer

This article aims at investigating the differences among three groups having distinct levels of experience in massively multiplayer online role-playing games (MMORPG), when solving a character design task in the videogame World of Warcraft (WoW), and when planning how to use the character during gameplay. These groups consisted of inexperienced players, general experts in MMORPGs and specialized WoW domain experts. The evaluation showed that MMORPG experience developed character design abilities that could be applied to other videogames (e.g., general expertise skills). Such skills were related to the ability to identify deep features related to particular types of characters (e.g., Rogue). The results also showed that there are domain expertise specific abilities, which only experts in WoW have. Such abilities were related to building game descriptions that could be considered narrative in the cognitive sense of the term, because they include time, intention and interaction, and also to identifying WoW-specific variables.

The XML Expert's Path to Web Applications

2016 ◽  
Author(s):  
Anne Brüggemann-Klein
Keyword(s):  
Web Applications ◽  
Implementation Strategies ◽  
Modeling Languages ◽  
End User ◽  
Domain Experts ◽  
Xml Documents ◽  
Modeling Techniques ◽  
Golden Opportunity ◽  
Domain Expertise ◽  
Xml Technologies

Web applications offer a golden opportunity for domain experts who work with XML documents to leverage their domain expertise, their knowledge of document engineering principles, and their skills in XML technology. Current XML technologies provide a full stack of modeling languages, implementation languages, and tools for Web applications that is stable, platform independent, and based on open standards. Combining principles and proven practices from document and software engineering, we identify architectures, modeling techniques, and implementation strategies that let end-user developers who are conversant with XML technologies create their own Web applications.

scholarly journals Fatigue Strength Evaluation for Remanufacturing Impeller of Centrifugal Compressor Based on Modified Grey Relational Model

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Qingchao Sun ◽  
Bowen Shi ◽  
Xiaokai Mu ◽  
Kepeng Sun
Keyword(s):  
Experimental Data ◽  
Fatigue Strength ◽  
Transformation Method ◽  
Relational Theory ◽  
Relational Model ◽  
Target Strength ◽  
Correction Function ◽  
Strength Data ◽  
Grey Relational ◽  
Target Data

The fatigue strength, as the essential basis of residual life evaluation, is required to be obtained timely for remanufacturing. Since impeller damage is characterized with very-high-cycle fatigue (VHCF), it is difficult to directly test the strength data. The transformation method of multisource strength data is proposed to predict fatigue strength for impeller based on grey relational theory. The multisource strength data, as factor space, primarily include available existing experimental data and operating data, while the strength data of the remanufacturing impeller are taken as target data. The fatigue strength model of material and component are presented to analyze the influence factors of remanufacturing target strength. And similar material provides a theoretical basis for selecting reference data reasonably. Considering the correlation and difference between available data and target data, the grey relational function is established, and the correction function of the target residual is brought forward to reduce the transformation deviation. The entropy-weight theory is implemented to determine the different impacts of multisource data on target strength. A test case, predicting the unknown impeller fatigue strength with various impellers, is applied to validate the proposed transformation method, and the results show that the predicted strength data are consistent with the experimental data well.

Sign in / Sign up

Export Citation Format

Share Document