The following events are co-located with LDK 2019:
Translation Inference across Dictionaries (TIAD)
TIAD’19 workshop will present results of the second shared task on Translation Inference Across Dictionaries, following on the first TIAD shared task and workshop held at
LDK’17. The objective is to explore and compare methods and techniques to infer translations indirectly between language pairs, based on existing bilingual resources from the Apertium RDF graph, which includes 22 RDF dictionary sets. Such techniques would help in auto-generating new bilingual and multilingual dictionaries based on existing ones. The participating systems will be asked to indirectly generate translations among three languages, namely Portuguese, French and English, which are not directly connected in the Apertium RDF graph. Participants will apply their methods and techniques to discover indirect translations (mediated by any other language in the graph) between the pairs: (EN, FR), (FR, PT), and (PT, EN), and will also be able to make use of other freely available sources of background knowledge to improve performance, as long as no direct translations among the final language pairs are used. Evaluation of the results will be carried out against manually compiled pairs of K Dictionaries. Participants will submit a system paper that should include a description of the system, the way the data have been processed, the applied algorithms, the obtained results, as well as the conclusions and ideas for future improvements. The papers will be peer reviewed prior to publication.
Historical Text Reuse Tutorial (TRACER)
The tutorial addresses participants who are interested in finding text reuse between two or multiple texts (in the same language). It teaches them how to explore, use and semi-automatically run the TRACER tool, a suite of state-of-the-art Natural Language Processing (NLP) algorithms and functions aimed at discovering text reuse in multifarious corpora from multiple genres. It is designed to work with historical text, such as Ancient Greek, Latin, Classical Arabic or medieval German, and provides researchers with a powerful engine to identify and display different types of text reuse ranging from verbatim quotations to paraphrase. To do so, TRACER implements basic NLP measures and operations, such as shingling and winnowing, and supplies an inbuilt, step-wise pipeline which breaks down the challenging task of reuse detection into smaller sub-tasks. A human-readable and editable configuration file gives the user full control over the parameters during every step, thus accommodating specific needs.
13th DBpedia Community Meeting
Following the LDK conference the DBpedia Community will get together on 23rd of May 2019. The 13th edition of the DBpedia Community Meeting covers the DBpedia Association hour and the NLP & DBpedia session. During the Showcase Session, the DBpedia community will present several selected showcases which will highlight the benefits of using and working with DBpedia. The DBpedia meeting enables the community to learn about the advancements of the largest Linked Open Data repository in existence – let them inspire you or contribute yourself towards shaping further progress among DBpedia enthusiasts!