Second Workshop on Natural Language Processing and Linked Open Data (NLP&LOD2)

Публикации

Collocated with RANLP 2015

11 September 2015

Hissar, Bulgaria

Workshop Proceedings

Workshop Programme

Accepted Papers

Submission deadline: *10 July 2015* EXTENDED!!!

Description

NLP started to use extensively LOD in various scenarios, such as: exploring knowledge datasets (DBPedia, FreeBase, GeoNames, etc.) for annotation and information extraction; publishing language resources as LOD (WordNet, FrameNet, etc.); aggregating of the available data for various tasks (BabelNet, Global WordNet Grid); creation of standards for LOD (LEMON); building ontologies for different domains.

At the same time, the NLP processing pipelines have been developed towards the recognition and extraction of entities and events from raw stream data. Handling of events, however, requires also the inclusion of high quality modules like NER, NED, Semantic Role Labeling (SRL), sense and valency annotation. These modules rely not only on canonical resources, but also on the LOD datasets for extracting information about people, facts, and organizations. Additionally NLP techniques are used for creation of LOD datasets on the basis of new textual information.

Since there is some experience gained now in the interaction between NLP and LOD as well as between LOD and NLP, some problems have been identified, too. These are: general failure of NLP technology to meet completely the requirements of LOD; incompleteness of LOD datasets; sparseness of LOD datasets through various languages and domains; lack of robust reasoning mechanisms in NLP and LOD; still inefficient handling of natural language non-literal phenomena, such as metonymy, polysemy, figurative expressions; usability and re-usability of NLP and LOD applications.

The workshop aims at gathering NLP researchers and developers, interested in hybrid NLP methods and enhancing its connections to LOD. It especially invited papers on the problematic issues in NLP and LOD within the context of their interaction.

Topics of interest

  • NLP processing for LOD: reasons for low precision and inconsistencies
  • Enhancing NLP applications with LOD
  • Information extraction from LOD using NLP techniques
  • Manipulating LOD (cleaning, adding information, deleting information, reconstructing facts) with NLP techniques
  • LOD as a corpus
  • Mapping LOD to common sense ontologies and language data
  • Storing LOD in RDF bases
  • Methodological and theoretical approaches to LOD
  • Handling polysemy and metonymy of entities in LOD
  • Incompleteness of LOD data
  • LOD as unbalanced data through countries, cultures and topics of interest
  • Insufficient reasoning in NLP and LOD
  • Dynamics of LOD & NLP: versioning, replication, provenance, etc.

Important dates

  • Submission deadline: *10 July 2015* EXTENDED!!!
  • Notification of acceptance: 7 August 2015
  • Camera-ready copies due: 22 August 2015
  • Workshop date: 11 September 2015

Submission

Multiple submission policy: We welcome papers that are under review for other venues, but, in the event of multiple acceptances, authors are requested to notify us and choose which meeting to present and publish the work at as soon as possible – we cannot accept for publication or presentation work that will be (or has been) published elsewhere.

Reviewing: Reviewing will be blind. No information identifying the authors should be in the paper: this includes not only the authors’ names and affiliations, but also self-references that reveal authors’ identities; for example, „We have previously shown (Smith 1999)“ should be changed to „Smith (1999) has previously shown“.

Paper length and presentation: We invite long (8) and short (4) papers. Accepted short papers will be presented either as short oral presentations or as posters.

Submission format: Authors should follow the RANLP’2015 submission format and paper size. The submissions should be uploaded via START system: Submission NLP&LOD2.

Invited speakers

German Rigau

Cross-lingual Event Detection in Discourse

Organizers

  • Piek Vossen, VU University Amsterdam
  • German Rigau, University of the Basque Country
  • Petya Osenova, Sofia University, Bulgaria
  • Kiril Simov, Bulgarian Academy of Sciences, Bulgaria

Programme committee

  • Eneko Agirre, University of the Basque Country, Spain
  • Kalina Boncheva, Sheffield University, UK
  • António Branco, University of Lisbon, Portugal
  • Aljoscha Burchardt, DFKI, Germany
  • Nicoletta Calzolari, Istituto di Linguistica Computazionale, Italy
  • Philipp Cimiano, University of Bielefeld, Germany
  • Christian Chiarcos, Goethe-University Frankfurt am Main, Germany
  • Thierry Declerck, DFKI, Germany
  • Markus Egg, Humboldt-University Berlin, Germany
  • Jan Hajič, Charles University in Prague, Czech Republic
  • John McCrae, University of Bielefeld, Germany
  • Petya Osenova, Sofia University and IICT-BAS, Bulgaria
  • Maciej Piasecki, Wroclaw University of Technology, Poland
  • German Rigau, University of the Basque Country, Spain
  • Felix Sasaki, DFKI, Germany
  • Kiril Simov, IICT-BAS, Bulgaria
  • Gertjan van Noord, University of Groningen, The Netherlands
  • Piek Vossen, Vrije Universiteit Amsterdam, The Netherlands