The SML16 Workshop was successfully held on July 10, 2016. Thanks to all for making it a success.

You can check out the Proceedings, presentation slides, videos below.

Aim and Scope

Learning is an important attribute of an AI system that enables it to adapt to new circumstances and to detect and extrapolate patterns. Machine Learning (ML) has seen a tremendous growth during the last few years due in part to the successful commercial deployments in products developed by major companies such as Google, Apple and Facebook. The interest has also being fuelled by the recent research breakthroughs brought about by deep learning. ML is however not a silver bullet as it is made out to be, and currently has several limitations in complex real-life situations. Some of these limitations include: i) many ML algorithms require large number of training data that are often too expensive to obtain in real-life, ii) significant effort is often required to do feature engineering to achieve high performance, iii) many ML methods are limited in their ability to exploit background knowledge, and iv) lack of a seamless way to integrate and use heterogeneous data.

Approaches that formalize data, functional and domain semantics, can tremendously aid addressing some of these limitations. The so-called semantic approaches have been increasingly investigated by various research communities and applied at different layers of ML, e.g. modeling representational semantics in vector space using deep learning architectures, and modeling domain semantics in ontology-based ML. This is complemented by the significant body of technologies and standards put together by the Semantic Web community that not only can facilitate greater industry adoption but can also enable incorporation of reasoning and inference in ML.

This workshop will bring together researchers and practitioners from all these communities working on different aspects of semantic ML, to share their experiences, exchange new ideas as well as to identify key emerging topics and define future directions.

Final Programme

    Date: July 10, 2016, Sunday
    Time: 8:30AM-12:30PM
    Venue: GREEN Room, L4 (Map), New York Hilton Midtown Hotel, NY City

    Download Pre-proceedings

Welcome Message by Chairs
08:30 – 09:10 KeyNote 1

Title: Video and language: where does domain,knowledge fit in? (Abstract | Slides)
Speaker: Prof. Jiebo Luo, Univ. of Rochester

09:10 – 10:30 Paper Session (4 papers – each 15 min + 5 min Q&A)

    1. Bassem Makni and James Hendler. Deep Learning of RDFS rules (PDF | Slides)
    2. Giuseppe Rizzo, Claudia D'Amato, Nicola Fanizzi and Floriana Esposito. Inducing Predictive Clustering Trees for Datatype Properties Values (PDF)
    3. Sanjaya Wijeratne, Lakshika Balasuriya, Derek Doran and Amit Sheth. Word Embeddings to Enhance Twitter Gang Member Profile Identification (PDF | Slides)
    4. Meriem Beloucif and Dekai Wu. A semantically confidence-weighted ITG induction algorithm (PDF)
10:30 – 11:00 COFFEE BREAK
11:00 – 11:40 KeyNote 2

Title: Learning from Complex Data (Abstract)
Speaker: Prof. Jennifer Dy, Northeastern

11:40 – 12:25 Panel Discussion

Title: Challenges and Prospects of integrating Semantics and Background Knowledge into Machine Learning
Panelists:

Dr. Biplav Srivastava

IBM

Prof. Peter Stone

University of Texas, Austin

Prof. Jie Tang

Tsinghua University

Video Recording:

12:25 – 12:30 Concluding Remarks

Accepted Papers


Bassem Makni and James Hendler. Deep Learning of RDFS rules
Giuseppe Rizzo, Claudia D'Amato, Nicola Fanizzi and Floriana Esposito. Inducing Predictive Clustering Trees for Datatype Properties Values
Sanjaya Wijeratne, Lakshika Balasuriya, Derek Doran and Amit Sheth. Word Embeddings to Enhance Twitter Gang Member Profile Identification
Meriem Beloucif and Dekai Wu. A semantically confidence-weighted ITG induction algorithm

Important Dates


Paper Submission: CLOSED
Author Notification: SENT
Camera ready: CLOSED
Workshop Date: 10 July 2016 (Morning)

(All deadlines are 11:59PM Hawaii time.)

Workshop Organisation


Chairs

Advisory Committee

  • Prof Amit Sheth, Wright State University, USA
  • Prof. Jane Hunter, University of Queensland, Australia
  • Prof. Fausto Giunchiglia, University of Trento, Trento, Italy
  • Prof. Athman Bouguettaya, RMIT University, Australia

Programme Committee

  • Armando Stellato, University of Roma Tor Vergata, Italy
  • Md.Sumon Shahriar, CSIRO, Australia
  • Heiko Mueller, New York University, USA
  • Flora Salim, RMIT University, Australia
  • Kim Jung Jae, Institute for Infocomm Research, Singapore
  • Prem Jayaraman, RMIT University, Australia
  • Robert Trypuz, John Paul II Catholic University of Lublin, Poland
  • Saeedeh Shekarpour, Knoesis, Wright State University, USA
  • Dr. Sherif Sakr, University of New South Wales (UNSW), Australia




Sections

Important Dates


Paper Submission: CLOSED
Author Notification: SENT
Camera ready: CLOSED
Workshop: Jul 10