We welcome papers documenting previously unpublished research; ongoing and exciting preliminary work is perfectly fine. We are particularly interested in visionary paper submissions. We aim for papers that express intriguing and promising ideas — focusing less on where science is today and more on where it should go tomorrow.

Topics of interest include, but are not limited to:

• machine learning on text; unsupervised, lightly-supervised and distantly-supervised learning; learning from naturally-available data
• deep learning for representing knowledge bases
• human-computer collaboration in knowledge base construction; automated population of wikis
• inference for graphical models and structured prediction; scalable approximate inference
• information extraction; open information extraction, named entity extraction; ontology construction
• entity resolution, relation extraction, information integration; schema alignment; ontology alignment; monolingual alignment, alignment between knowledge bases and text
• pattern analysis, semantic analysis of natural language, reading the web, learning by reading
• databases; distributed information systems; probabilistic databases
• scalable computation; distributed computation
• question-answering using KBs, queries on mixtures of structured and unstructured data; querying under uncertainty
• dynamic data, online/on-the-fly adaptation of knowledge
• languages, toolkits and systems for automated knowledge base construction
• demonstrations of existing automatically-built knowledge base

In addition, for the first time, AKBC will address a longstanding issue in the AKBC, that of equitable comparison and evaluation across methods. We encourage people to use the KBP Online platform (https://kbpo.stanford.edu/), a new effort to standardize KB population/construction evaluation, for their system evaluation for paper submissions. The platform automates the annotation of kb output and is made available for free for AKBC participants. For further details or questions, visit https://kbpo.stanford.edu/ or email chaganty@stanford.edu.

Invited Talks

• Xin Luna Dong (Amazon)
• Tom Mitchell (Carnegie Mellon University)
• Maximilian Nickel (Facebook AI Research)
• Sebastian Riedel (Bloomsbury AI / University College London)
• Sameer Singh (University of California, Irvine)
• Ivan Titov (University of Edinburgh)
• Luke Zettlemoyer (University of Washington / Allen Institute for Artificial Intelligence)

Submission

Please format your papers using the standard NIPS 2017 style files, and restrict them to 5 pages (excluding references). Since the reviewing will not be double-blind, include author information and the \nipsfinalcopy flag. Note that you don't have to include a separate Abstract section in the submission. All accepted papers will be presented as posters, with exceptional submissions also presented as oral talks.

• Style files: https://nips.cc/Conferences/2017/PaperInformation/StyleFiles
• Submission site: https://easychair.org/conferences/?conf=akbc2017

Student Travel Award

We are happy to announce that this year we are able to award free workshop registration to exceptional student applicants. Please send your CV and a short cover letter explaining why you need the travel award, your research interests and how it fits to AKBC to info@akbc.ws.

Important Dates

• Submission Due: October 21, 2017
• Student Travel Award Application Due: October 22, 2017
• Notification: November 5, 2017
• Camera-ready Due: November 12, 2017
• Workshop: December 8, 2017

Organizers

• Jay Pujara, Information Sciences Institute, USA
• Danqi Chen, Stanford University, USA
• Bhavana Dalvi, Allen Institute for Artificial Intelligence, USA
• Tim Rocktäschel, University of Oxford, UK