AKBC 2016

5th Workshop on Automated Knowledge Base Construction (AKBC) 2016

at NAACL 2016 in San Diego, California, June 17, 2016.

Slides from the invited and contributed talks are available!

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 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, AKBC 2013 and AKBC 2014 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, Stanford, University of Washington, CMU, University of Massachusetts, and more), and DARPA. With this year’s workshop, we aim to resume this positive experience. By 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:

  • machine learning on text; unsupervised, lightly-supervised and distantly-supervised learning; learning from naturally-available data
  • 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
  • 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 bases

With this year’s workshop, we would like to resume the positive experiences from three previous workshops: AKBC-2010, AKBC-WEKEX-2012, AKBC 2013, and AKBC 2014. The AKBC-2016 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.

Our workshop highly values the open exchange of ideas, the freedom of thought and expression, and respectful scientific debate. We support and uphold the NAACL Anti-Harassment policy, and any workshop participant should feel free to contact any of the NAACL Board members or Priscilla Rasmussen, in case of any issues.

Antoine Bordes Facebook Artificial Intelligence Research
William Cohen Carnegie Mellon University
Benjamin Van Durme Johns Hopkins University
Oren Etzioni Allen Institute for Artificial Intelligence
Percy Liang Stanford University
Chris Manning Stanford University
Andrew McCallum University of Massachusetts Amherst
Kristina Toutanova Microsoft Research

Friday, June 17th, 2016

Start End Speaker Title
9:00 9:10 AKBC Organizers Opening Remarks
9:10 9:40 Kristina Toutanova Joint Compositional Learning from Text and Knowledge Bases (slides)
9:40 10:10 Oren Etzioni The Allen AI Science Challenge: Results, Lessons, and Open Questions (slides)
10:10 11:00 Morning Poster Session and Coffee Break
11:00 11:30 Andrew McCallum Universal Schema for Representation and Reasoning from Natural Language
11:30 12:00 William Cohen Look Ma, No Neurons: Using Explicit Inference Rules to Complete a KB (slides)
12:00 1:20 Lunch Break and Morning Posters
1:20 1:35 Stuart Russell, Ole Torp Lassen, Justin Uang, Wei Wang Contributed Talk: The Physics of Text: Ontological Realism in Information Extraction (slides)
1:35 1:50 Sreyasi Nag Chowdhury, Niket Tandon, Gerhard Weikum Contributed Talk: Know2Look: Commonsense Knowledge for Visual Search (slides)
1:50 2:15 Christopher Manning Texts as Knowledge Bases (slides)
2:15 2:40 Benjamin Van Durme Common Sense and Language
2:40 2:55 Patrick Verga, Andrew McCallum Contributed Talk: Row-less Universal Schema (slides)
2:55 3:10 Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, Sebastian Riedel Contributed Talk: An Attentive Neural Architecture for Fine-grained Entity Type Classification (slides)
3:10 4:00 Afternoon Poster Session and Coffee Break
4:00 4:25 Percy Liang Querying Unnormalized and Incomplete Knowledge Bases (slides)
4:25 4:50 Antoine Bordes Memory Networks for Language Understanding: Successes and Challenges (slides)
4:50 5:30 Christopher Manning, Benjamin Van Durme, Percy Liang,
Antoine Bordes
Afternoon Speaker Panel
5:30 5:45 AKBC Organizers Closing Remarks

Morning Posters

Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction [PDF]
Lidong Bing, William Cohen, Bhuwan Dhingra and Richard Wang
Discovering Entity Knowledge Bases on the Web [PDF]
Andrew Chisholm, Will Radford and Ben Hachey
IKE - An Interactive Tool for Knowledge Extraction [PDF]
Bhavana Dalvi, Sumithra Bhakthavatsalam, Chris Clark, Peter Clark, Oren Etzioni, Anthony Fader and Dirk Groeneveld
Incorporating Selectional Preferences in Multi-hop Relation Extraction [PDF]
Rajarshi Das, Arvind Neelakantan, David Belanger and Andrew McCallum
Knowledge Base Population for Organization Mentions in Email [PDF]
Ning Gao, Mark Dredze and Douglas Oard
Enriching Wikidata with Frame Semantics [PDF]
Hatem Mousselly Sergieh and Iryna Gurevych
Demonyms and Compound Relational Nouns in Nominal Open IE [PDF]
Harinder Pal and Mausam
But What Do We Actually Know? [PDF]
Simon Razniewski, Fabian Suchanek and Werner Nutt
Learning Knowledge Base Inference with Neural Theorem Provers [PDF]
Tim Rocktäschel and Sebastian Riedel

Afternoon Posters

Know2Look: Commonsense Knowledge for Visual Search [PDF] [Contributed Talk]
Sreyasi Nag Chowdhury, Niket Tandon and Gerhard Weikum
Regularizing Relation Representations by First-order Implications [PDF]
Thomas Demeester, Tim Rocktäschel and Sebastian Riedel
Applying Universal Schemas for Domain Specific Ontology Expansion [PDF]
Paul Groth, Sujit Pal, Darin McBeath, Brad Allen and Ron Daniel
Design of Word Association Games using Dialog Systems for Acquisition of Word Association Knowledge [PDF]
Yuichiro Machida, Daisuke Kawahara, Sadao Kurohashi and Manabu Sassano
Call for Discussion: Building a New Standard Dataset for Relation Extraction Tasks [PDF]
Teresa Martin, Fiete Botschen, Ajay Nagesh and Andrew McCallum
The Physics of Text: Ontological Realism in Information Extraction [PDF] [Contributed Talk]
Stuart Russell, Ole Torp Lassen, Justin Uang and Wei Wang
An Attentive Neural Architecture for Fine-grained Entity Type Classification [PDF] [Contributed Talk]
Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui and Sebastian Riedel
A Comparison of Weak Supervision methods for Knowledge Base Construction [PDF]
Ameet Soni, Dileep Viswanathan, Niranjan Pachaiyappan and Sriraam Natarajan
Row-less Universal Schema [PDF] [Contributed Talk]
Patrick Verga and Andrew McCallum
A Factorization Machine Framework for Testing Bigram Embeddings in Knowledgebase Completion [PDF]
Johannes Welbl, Guillaume Bouchard and Sebastian Riedel
Call for Papers
December 1, 2015
Submission Due
March 25, 2016
April 1, 2016
Camera-ready Due
April 8, 2016
June 17, 2016

Deadlines are at 11:59pm PDT, and subject to change.

For any questions, please mail info@akbc.ws

Program Committee

  • Alan Akbik
  • Gabor Angeli
  • Stephen Bach
  • Niranjan Balasubramanian
  • Guillaume Bouchard
  • Eunsol Choi
  • Bhavana Dalvi
  • Doug Downey
  • Luis Galarraga
  • Matt Gardner
  • Anna Lisa Gentile
  • Adam Grycner
  • Roman Klinger
  • Sebastian Krause
  • Jayant Krishnamurthy
  • Omer Levy
  • Victoria Lin
  • Xiao Ling
  • Daniel Lowd
  • Ndapandula Nakashole
  • Jason Naradowsky
  • Arvind Neelakantan
  • Hoifung Poon
  • Pontus Stenetorp
  • Niket Tandon
  • Philippe Tomas
  • Larysa Visengeriyeva
  • Andreas Vlachos
  • Bishan Yang