Call for Papers

While the amount of Linked Open Data (LOD) increases rapidly, it is still used mostly by Semantic Web experts. Two main obstacles make the billions of RDF triples already available hard to access for common Web users: the need to learn the query language SPARQL and the need to know the schemas underlying the datasets. Approaches to addressing these obstacles include graphical query interfaces, agent-based systems, and natural language interfaces. This workshop targets advances in the creation of natural language interfaces for the Web of Data as this category of interfaces is receiving an increasing interest due to their high expressive power and the ease of use. For example, recent progresses in speech recognition technologies (e.g., Siri, Google Voice) demonstrate the usefulness of natural-language interfaces for accessing large amounts of (partly structured) data.

NLIWoD 2017’s goal is to bring together experts on the use of natural-language interfaces (NLI) for answering questions especially over the Web of Data.

Topics of interest include but are not limited to:

    • NEW! Dialogue systems

    • NEW! Personal assistants

    • NEW! Chatbots

    • Question answering over Linked Data

    • Benchmarking natural language interfaces

    • Term matching and entity disambiguation

    • Browsing Linked Data

    • Indexing for question answering

    • Deep Learning for Natural Language Interaction

    • SPARQL query pattern generation

    • Schema-agnostic query generation

    • Discovery of Linked Data sources

    • Endpoint profiling

    • Dealing with data and schema heterogeneity

    • Providing justifications of answers and conveying trust

    • Knowledge base design for question answering

    • Language resources and NLP software for question answering

    • Reasoning for question answering

    • Natural language querying of RDF exposed as Linked Data

    • Natural language querying of Web services

    • User feedback and interaction

Submission Instructions

NLIWoD 2017 solicits the submission of original research papers in two types:

  • Full paper submissions (up to 16 pages) must describe substantial and original work.

  • Short paper submissions (up to 8 pages) must describe an original work which may present

    • A small, focused contribution,

    • A work in progress, or

    • An interesting application case.

  • Demos and posters presentations (up to 4 pages)

All submissions must be in English and in PDF formatted the style of the Springer Publications format for Lecture Notes in Computer Science (LNCS). For details on the LNCS style, see Springer's Author Instructions. All papers are to be submitted via EasyChair (https://easychair.org/conferences/?conf=nliwod3). All submissions will be peer-reviewed by the Program Committee of the workshop. Submissions do not need to be anonymous.