Filters








8 Hits in 7.3 sec

Human-in-the-Loop Challenges for Entity Matching

AnHai Doan, G. C. Paul Suganthan, Haojun Zhang, Adel Ardalan, Jeffrey Ballard, Sanjib Das, Yash Govind, Pradap Konda, Han Li, Sidharth Mudgal, Erik Paulson
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
We discuss how such solution architectures can be viewed as combining "tools in the loop" with "human in the loop".  ...  Entity matching (EM) has been a long-standing challenge in data management. In the past few years we have started two major projects on EM (Magellan and Corleone/Falcon).  ...  , 2017, Chicago, IL, USA c 2017 ACM.  ... 
doi:10.1145/3077257.3077268 dblp:conf/sigmod/DoanABDGKLMPCZ17 fatcat:drf2u2mrejcntjk47myhrqxa7q

Precision Interfaces

Haoci Zhang, Thibault Sellam, Eugene Wu
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
To address this problem, we present Precision Interfaces, a semi-automatic system to generate task-specific data analytics interfaces.  ...  This paper focuses on SQL query logs, but we can generalize the approach to other languages.  ...  Acknowledgements: We thank Yifan Wu, who provided the initial inspiration for this project, and Laura Rettig who worked on early formulations of the problem.  ... 
doi:10.1145/3077257.3077261 dblp:conf/sigmod/ZhangS017 fatcat:jreqb7g6hvfv7d57hs7dydl4nm

SOCRAT Platform Design

Alexandr A. Kalinin, Selvam Palanimalai, Ivo D. Dinov
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
We present the preliminary design and implementation of an open-source platform for Statistics Online Computational Resource Analytical Toolbox (SOCRAT). is platform de nes: (1) a speci cation for an architecture  ...  To address these challenges, we consider the design requirements for the development of a module-based VA system architecture, adopting existing practices of large scale web application development.  ...  panel (2b), (3) interactive clustering module with the results of k-means, (4) interactive histogram with variable number of bins. 17, Chicago, IL, USA © 2017 Copyright held by the owner/author(s).  ... 
doi:10.1145/3077257.3077262 pmid:29630069 pmcid:PMC5884130 dblp:conf/sigmod/KalininPD17 fatcat:qo47n2sxtrd5pn6xrionavwcqm

A Game-theoretic Approach to Data Interaction

Ben McCamish, Arash Termehchy, Behrouz Touri
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
Database systems usually improve their understanding of users' intents by collecting their feedback on the answers to the users' imprecise and ill-specified queries.  ...  In this paper, we report our progress on developing a formal framework for representing and understanding information needs in database querying and exploration.  ...  HILDA'17, Chicago, IL, USA © 2017 ACM. 978-1-4503-5029-7/17/05. . . $15.00 DOI: http://dx.doi.org/10.1145/3077257.3077270 (z ) ← Gr ade ( ohn, 'Smit h', , z ) e 2 ans (z ) ← Gr ade (K er r , 'Smit h'  ... 
doi:10.1145/3077257.3077270 dblp:conf/sigmod/McCamishTT17 fatcat:xkfielf4t5glfjlitel37upqxi

PALM

Sanjay Krishnan, Eugene Wu
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
While there are many models for interpretability in terms of predictive features, it may be more natural to isolate a small set of training examples that have the greatest influence on the prediction.  ...  However, it is often the case that every training example contributes to a prediction in some way but with varying degrees of responsibility.  ...  HILDA'17, Chicago, IL, USA © 2017 ACM. 978-1-4503-5029-7/17/05. . . $15.00 DOI: http://dx.doi.org/10.1145/3077257.3077271 Figure 1 : 1 (Left) ML developers need to understand the relationship between  ... 
doi:10.1145/3077257.3077271 dblp:conf/sigmod/Krishnan017 fatcat:aea6e7xw2fbiviupwnxu2kqtty

Assisting Discovery in Public Health

Yannis Katsis, Nikos Koulouris, Yannis Papakonstantinou, Kevin Patrick
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
PHD generalizes the current workflow of PH researchers by facilitating the major analytics tasks involved in PH discovery, such as calculating important associations based on the standard notions of odds  ...  We show that data-driven studies can be effective and yet avoid the potential pitfalls by keeping the researchers in the loop of the discovery process.  ...  Once we have solved the technical problems, we will be evaluating the PHD platform with public health experts in the DELPHI project. HILDA' 17 , 17 May 14, 2017, Chicago, IL, USA c 2017 ACM.  ... 
doi:10.1145/3077257.3077269 dblp:conf/sigmod/KatsisKPP17 fatcat:bjmpbiihzrfzxnh3vknxpfdzcu

Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations

Paolo Tamagnini, Josua Krause, Aritra Dasgupta, Enrico Bertini
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
To realize the full potential of machine learning in diverse realworld domains, it is necessary for model predictions to be readily interpretable and actionable for the human in the loop.  ...  Analysts, who are the users but not the developers of machine learning models, often do not trust a model because of the lack of transparency in associating predictions with the underlying data space.  ...  The research described in this paper is part of the Analysis in Motion Initiative at Paci c NorthWest National Laboratory (PNNL).  ... 
doi:10.1145/3077257.3077260 dblp:conf/sigmod/TamagniniKDB17 fatcat:25frf6jujbhrncjaji5vablcuq

ProvDB

Hui Miao, Amit Chavan, Amol Deshpande
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
As data-driven methods are becoming pervasive in a wide variety of disciplines, there is an urgent need to develop scalable and sustainable tools to simplify the process of data science, to make it easier  ...  simplify bookkeeping and debugging tasks but also enable a rich new set of capabilities like identifying aws in the data science process itself.  ...  HILDA'17, Chicago, IL, USA © 2017 ACM. 978-1-4503-5029-7/17/05. . . $15.00 DOI: http://dx.doi.org/10.1145/3077257.3077267 the right analysis tools, models, and parameters.  ... 
doi:10.1145/3077257.3077267 dblp:conf/sigmod/MiaoCD17 fatcat:ofr25bj2trewri4ksbwtq3wxgu