This volume contains the papers presented at HumL@ISWC2018, the second international workshop on Augmenting Intelligence with Humans-in-the-Loop held on October 9, 2018 in Monterey, CA in conjunction with the 17th International Semantic Web Conference (http://iswc2018.semanticweb.org/). Humans-in-theloop is a model of interaction where a machine process and one or more humans have an iterative interaction. In this paradigm the user has the ability to heavily in uence the outcome of the process by providing feedback to the system as well as the opportunity to grab di erent perspectives about the underlying domain and understand the step by step machine process leading to a certain outcome. Amongst the current major concerns in Arti cial Intelligence research are being able to explain and understand the results as well as avoiding bias in the underlying data that might lead to unfair or unethical conclusions. Typically, computers are fast and accurate in processing vast amounts of data. People, however, are creative and bring in their perspectives and interpretation power. Bringing humans and machines together creates a natural symbiosis for accurate and unbiased interpretation of data at scale. The goal of this workshop is to bring together researchers and practitioners in various areas of AI and Semantic Web to explore new pathways of the humans-in-the-loop paradigm.
The workshop program covers diverse application domains and problems where humans-in-the-loop approaches have been studied. Example applications include language models for dictionary expansion, hiring decisions, knowledge graph curation, and active learning, which is a perfect example of humans-inthe-loop approaches that aim at optimally combining humans and algorithms together. Other aspects considered in our proceedings are the interaction of multiple humans when supporting algorithmic decision making and the selection of the right compensation level for humans involved in data annotation tasks. Crowd-sourcing Updates of Large Knowledge Graphs : : : : : : : : : : : : : : : : : : Albin Ahmeti, Victor Mireles, Artem Revenko, Marta Sabou and Martin Schauer Interactive Dictionary Expansion using Neural Language Models : : : : : : : :
Alfredo Alba, Daniel Gruhl, Petar Ristoski and Steve Welch Making Better Job Hiring Decisions using "Human in the Loop" Techniques : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :
Christopher G. Harris Use of internal testing data to help determine compensation for crowdsourcing tasks : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :
Michael Lauruhn, Paul Groth, Corey Harper and Helena Deus Rank Scoring via Active Learning (RaScAL) : : : : : : : : : : : : : : : : : : : : : : : : :
Jack O'Neill, Sarah Jane Delany and Brian Mac Namee ESO-5W1H Framework: Ontological model for SITL paradigm : : : : : : : : : : Shubham Rathi and Aniket Alam 1 7 16 27 38 51 Lora Aroyo Michele Catasta Irene Celino Anni Coden Philippe Cudre-Mauroux Gianluca Demartini Djellel Difallah Giorgio Maria Dinunzio Anca Dumitrache Anna Lisa Gentile Daniel Gruhl Oana Inel Ismini Lourentzou Marta Sabou Cristina Sarasua Maja Vukovic Chris Welty Jie Yang Amrapali Zaveri
Vrije Universiteit Amsterdam Stanford University CEFRIEL IBM, TJ Watson Research Center U. of Fribourg The University of Queensland NYU University of Padua Vrije Universiteit Amsterdam IBM IBM Almaden Research Center Vrije Universiteit Amsterdam University of Illinois at Urbana - Champaign Vienna University of Technology University of Zurich IBM Google eXascale Infolab, University of Fribourg Maastricht University