About this workshop

Recently, some international initiatives such as the LIDER European project (www.lider-project.eu) and the W3C OntoLex, BPMLOD, and LD4LT community groups, as well as the Open Knowledge Foundation (OKFN) Working Group for Open Data in Linguistics (OWLG), have promoted an ecosystem of linguistic linked open data (LLOD) around which there is a growing community of interested stakeholders. Such an ecosystem comprises new linked data-based versions of well known families of language resources (e.g., Wordnets, Apertiums, annotated corpora...), guidelines and best practices on linguistic linked data and NLP services, and new representation models such as lemon-OntoLex and NIF. The above-mentioned initiatives have made possible the emergence of such a LLOD cloud, which will be the basis for a new generation of linked data-aware NLP services. One of the main motivations of this workshop is, precisely, to move the LLOD cloud from its current stage into a next phase in which innovative applications will be developed on top of it, aimed to overcome the language barriers on the Web.

LIDER and the LLOD originated in the NLP and language resource communities and we believe this workshop will provide a forum for interaction of computational linguists, NLP researchers, and the language technology industry with Semantic Web practitioners. Furthermore we intend to instigate cross-continent community collaboration between the European-oriented movement and Asian efforts.

To integrate or link language/knowledge resources across languages will greatly enhance the utility and usability of these resources. For example, the EDR Electronic Dictionary (with 400k concept nodes with over 900k relations), developed as a Japanese national project more than 20 years ago, would regain its value by integrated with other resources as a part of LLOD. The resulted resource then would be effectively utilized in a variety of cross-language applications. However actually realizing this scenario would require sophisticated methodologies, since the underlying conceptualization, somewhat reflecting Japanese/Asian way of thinking and world recognition, may largely different from that of, for example, Europe. In addition, extending the LLOD representation framework to incorporating these varieties would be necessary.


Invited Speaker

Yohei Murakami

Unit of Design,
Center for the Promotion of Interdisciplinary Education and Research,
Kyoto University

Yohei Murakami received his PhD degree in informatics from Kyoto University, Kyoto, Japan, in 2006. He is now an associate professor of Unit of Design at Kyoto University. His research interests lie in services computing and multi-agent systems, and he has been working on the language grid, a multi-language service infrastructure built by applying the above technologies to natural language processing, for almost ten years. He founded International Workshop on Worldwide Language Service Infrastructure in 2013, which aims to make the existing platforms interoperable. He was a recipient of the 2012 Achievement Award of the Institute of Electronics, Information and Communication Engineers.


Organizers

Support Committee


Program

9:00-9:30Welcome - Sebastian Hellmann & Jorge Gracia
9:30-10:30Yohei Murakami - The Language Grid: Towards an Interoperable Language Service Infrastructure (invited talk)
10:30-11:00Coffee
11:00-11:40Andreas Niekler and Christian Kahmann - Extracting process graphs from medical text data
11:40-12:20Eun-Kyung Kim and Key-Sun Choi - Identifying Global Representative Classes of DBpedia Ontology through Multilingual Analysis: A Rank Aggregation Approach information on submission
12:20-14:00Lunch
14:00-14:40John P. McCrae and Narumol Prangnawarat - Identifying Poorly-Defined Concepts in WordNet with Graph Metrics
14:40-15:20Masaharu Yoshioka - WC3: Analyzing the style of metadata annotation among Wikipedia articles by using Wikipedia category and the DBPedia metadata database
15:30-16:00Coffee
16:00-16:20Mehwish Alam, Aldo Gangemi and Valentina Presutti - Framester Classic: Evaluating Linguistic Linked Data on Frame Detection (short talk)
16:20-17:00Felix Sasaski and Milan Dojchinovski - Chainable and Extendable Knowledge Integration Web Services

Call for Papers

What kind of smart applications can we build, if we were able to integrate all available knowledge, data and language resources in a meaningful way? In order to realize the dream of artificial intelligence, it is necessary to focus on the actual knowledge engineering to build information machines that enable humans to perform more efficiently in their tasks. To achieve this goal, we believe the following two prerequisites must be met:

Research in this workshop focuses on contextualising data and ontologies as well as capturing deep linguistic knowledge to improve machine understanding.

Purpose and scope

Some international initiatives such as the LIDER European project and the W3C OntoLex, BPMLOD, and LD4LT community groups, as well as the Open Knowledge Foundation (OKFN) Working Group for Open Data in Linguistics (OWLG), have promoted an ecosystem of linguistic linked open data (LLOD)

One of the main motivations of this workshop is to move the LLOD cloud to its next phase in which innovative applications will be developed overcoming the language barriers on the Web.

The KÉKI workshop is targeted at anyone interested in Semantic Web, Linguistics and Natural Language Processing technologies and we are especially welcoming submissions focussing on either domain topics or technological topics or both.

Domain Topics

Technological Topics

Submission Guidelines

We invite submissions in the form of regular long and short papers.

All workshop papers must represent original and unpublished work that is not currently under review. Papers will be evaluated according to their significance, originality, technical content, style, clarity, and relevance to the workshop. At least one author of each accepted paper is expected to attend the workshop upon acceptance.

All papers should follow the LNCS guidelines for formatting and should aim to be 10 pages in length for long papers and 6 pages for short papers, excluding references and optional appendices. The layout templates are available for download from the Springer website at https://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0

which also contains MS Office/Word instructions. The file format for submissions is Adobe Portable Document Format (PDF). Other formats will not be accepted.

Revised post-proceedings of accepted papers will be published as Springer Lecture Notes in Computer Science in collaboration with the NLP&DBpeida 2016 workshop

Submissions must be uploaded electronically by the submission deadline July 7th 2016 through EasyChair at:

https://easychair.org/conferences/?conf=kki2016

For any inquiries regarding the submission process or to request a deadline extension, please send an email to our public mailing list at keki2016@linguistic-lod.org.


Important Dates


Program Committee