Update: The workshop programme and the list of accepted papers are now online! Also, the conference proceedings are now available.

August 23, 2014, Dublin, Ireland

In this workshop, we are bringing together leading researchers in the emerging field of Information Discovery to discuss approaches for Information Extraction that are not bound by a pre-specified schema of information, but rather discover relational or categorial structure automatically from given unstructured data.

This includes approaches that are based on unsupervised machine-learning over models of distributional semantics, as well as OpenIE methods that relax the definition of semantic relations in order to more openly extract structured information. Other approaches focus on inexpensively training information extractors to be used across different domains with minimal supervision, or on adapting existing IE systems to new domains and relations.

As different approaches on Information Discovery are gaining momentum, many fundamental questions arise that merit discussion: How do these approaches compare and what are their relative strengths and weaknesses? What are the desiderata and applications for Information Discovery methods? How can such methods be evaluated and compared? And most importantly, what is the potential of Information Discovery methods and where can current research lead?

Invited Speakers:

Sebastian Riedel (University College London)

Sameer Singh (University of Washington)

Fabian Suchanek (Télécom ParisTech University)

Ce Zhang (University of Wisconsin-Madison)