4th Workshop on Automated Knowledge Base Construction (AKBC) 2014
at NIPS 2014 in Montreal, Canada, December 13, 2014.
Extracting knowledge from Web pages, and integrating it into a coherent knowledge base (KB) is a task that spans the areas of natural language processing, information extraction, information integration, databases, search, and machine learning. Recent years have seen significant advances here, both in academia and in the industry. Most prominently, all major search engine providers (Yahoo!, Microsoft Bing, and Google) nowadays experiment with semantic KBs. Our workshop serves as a forum for researchers on knowledge base construction in both academia and industry.
Unlike many other workshops, our workshop puts less emphasis on conventional paper submissions and presentations, but more on visionary papers and discussions. In addition, one of its unique characteristics is that it is centered on keynotes by high-profile speakers. AKBC 2010, AKBC 2012, and AKBC 2013 each had a dozen invited talks from leaders in this area from academia, industry, and government agencies. We had senior invited speakers from Google, Microsoft, Yahoo, several leading universities (MIT, University of Washington, CMU, University of Massachusetts, and more), and DARPA. With this year’s proposal, we would like to resume this positive experience. By inviting established researchers for keynotes, and by focusing particularly on vision paper submissions, we aim to provide a vivid forum of discussion about the field of automated knowledge base construction.
Topics of interest:
With this year’s workshop, we would like to resume the positive experiences from two previous workshops: AKBC-2010, AKBC-WEKEX-2012, and AKBC 2013. The AKBC-2014 workshop will serve as a forum for researchers working in the area of automated knowledge harvesting from text. By having invited talks by leading researchers from industry, academia, and the government, and by focusing particularly on vision papers, we aim to provide a vivid forum of discussion about the field of automated knowledge base construction.
|Tom Mitchell||Carnegie Mellon University, USA|
|Andrew McCallum||University of Massachusetts, Amherst, USA|
|Chris Re||Stanford University|
|Oren Etzioni||CEO, Allen Institute for Artificial Intelligence|
|William Cohen||Carnegie Mellon University, USA|
|Hoifung Poon||Microsoft Research|
|Jason Weston||Facebook Research||Boyan Onyshkevych||DARPA|
|Kevin Murphy||Google Research|
|8:30||8:45||Fabian Suchanek||Welcome Message (slides)|
|9:15||9:45||Andrew McCallum||Representation & Reasoning with Universal Schema & Embedded Representations||[Video]||9:45||10:00||Peter Clark||Contributed Talk: Automatic Construction of Inference-Supporting Knowledge Bases||[Video]|
|10:00||11:00||Poster Session + Break|
|11:30||11:45||Arvind Neelakantan||Contributed Talk: Knowledge Base Completion using Compositional Vector Space Models||[Video]|
|11:45||12:00||Ari Kobren||Contributed Talk: Domain Specific Knowledge Base Construction via Crowdsourcing||[Video]|
|12:00||12:30||Oren Etzioni||The View from AI2 (Slides)|
|12:30||2:30||Lunch + Poster Session|
|3:00||3:30||William Cohen||Scalable Joint Inference and Reasoning in Automatic KB Construction (Slides)||[Video]|
|3:30||4:00||Hoifung Poon||Machine Reading for Cancer Panomics (Slides)||[Video]|
|4:00||5:00||Poster Session + Break|
|5:00||5:30||Jason Weston||Embeddings for KB and text representation, extraction and question answering (Slides)||[Video]|
|5:30||6:00||Boyan Onyshkevych||KB Representation of Text, Audio, Images, and Video (Slides)||[Video]|
We welcome ongoing and exciting preliminary work. 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. All accepted papers will be presented as posters, with exceptional submissions also presented as oral talks.
Please format your papers using the standard NIPS Style files, and restrict it
to 4 pages (excluding references). Since the reviewing will not be double blind, please include author information and the
\nipsfinalcopy flag. Note that you don't have to include a separate
Abstract section in the submission.
Please use the above instructions, and the following link, to update your submission for camera-ready. The page limit for the camera-ready has been expanded to 5 pages (+ references). The camera-ready submissions are due by November 28.
Every talk should be accompanied by a poster. The maximal poster width is 1 meter (3 feet), which corresponds to A0 in portait orientation.