1st Joint International Workshop on
Entity-oriented and Semantic Search (JIWES) 2012


Located at the 35th ACM SIGIR Conference
Portland, Oregon, USA, August 12–16, 2012

News

2012-10-08: Proceedings are online in ACM DL
2012-09-10: Slides uploaded.
2012-09-06: Slides of Kaushik Chakrabarti's Keynote are online.
2012-08-24: Slides of John Shafer's Keynote are online.
2012-08-16: Best Contribution Award goes to the Team of the University of Freiburg for their presentation and paper!
2012-08-16: Workshop is today!
2012-08-13: Papers online!
2012-08-01: Program online!
2012-07-30: List of accepted papers online!
2012-07-13: John Shafer will give a keynote!
2012-07-06: Kaushik Chakrabarti will give a keynote!
2012-07-01: Paper deadline extended to July 9th.
2012-05-29: Workshop Web page is ready!

Important Dates

Submissions Due:
July 2,
extended July 9, 2012

Notification of Acceptance:
July 23, extended July 27, 2012

Camera Ready:
August 1, 2012

Workshop date:
August 16th, 2012

Workshop Support

Best Contribution Award is sponsored by Yandex

Program

08:45-09:00     Introduction
09:00-10:00     Keynote by John Shafer, Microsoft Research:
The Lincoln Project: Building a Web-Scale Semantic Search Engine
10:00-10:30    Coffee
10:30-12:10   
12:10-14:00    Lunch
14:00-15:00    Keynote by Kaushik Chakrabarti, Microsoft Research:
Simple Models, Lots of Data: Mining semantics about entities using Web-Scale Data
15:00-15.30    Coffee
15:30-16.50   
16:50-18:00    Panel/discussion + best paper award winner voting/awarding




List of accepted Papers:


  • Hadas Raviv, David Carmel and Oren Kurland.
    A Ranking Framework for Entity Oriented Search using Markov Random Fields (paper/slides)
  • Christos Koumenides and Nigel Shadbolt.
    Combining Link and Content-based Information in a Bayesian Inference Model for Entity Search (paper)
  • Christian Scheel and Alan Said.
    Semantic Preference Retrieval for Querying Knowledge Bases (paper/slides)
  • Jay Urbain.
    User-driven Relational Models for Entity-Relation Search and Extraction (paper)
  • Olga Vechtomova.
    A semi-supervised approach to extracting multiword entity names from user reviews (paper/slides)
  • Hannah Bast, Florian Bäurle, Björn Buchhold, and Elmar Haussmann.
    A Case for Semantic Full-Text Search (position paper) (paper/slides)

Short presentations:

  • Ming Zhong and Mengchi Liu.
    Ranking the Answer Trees of Graph Search by both Structure and Content (short presentation) (paper)
  • Suppawong Tuarob, Prasenjit Mitra and C. Lee Giles.
    Taxonomy-based Query-dependent Schemes for Profile Similarity Measurement (short presentation) (paper/slides)

About the Workshop

The workshop encompasses various tasks and approaches that go beyond the traditional bag-of-words paradigm and incorporate an explicit representation of the semantics behind information needs and relevant content. This kind of semantic search, based on concepts, entities and relations between them, has attracted attention both from industry and from the research community. The workshop aims to bring people from different communities (IR, SW, DB, NLP, HCI, etc.) and backgrounds (both academics and industry practitioners) together, to identify and discuss emerging trends, tasks and challenges. This joint workshop is a sequel of the Entity-oriented Search and Semantic Search Workshop series held at different conferences in previous years.

Topics

The workshop aims to gather all works that discuss entities along three dimensions: tasks, data and interaction. Tasks include entity search (search for entities or documents representing entities), relation search (search entities related to an entity), as well as more complex tasks (involving multiple entities, spatio-temporal relations inclusive, involving multiple queries). In the data dimension, we consider (web/enterprise) documents (possibly annotated with entities/relations), Linked Open Data (LOD), as well as user generated content. The interaction dimension gives room for research into user interaction with entities, also considering how to display results, as well as whether to aggregate over multiple entities to construct entity profiles. The workshop especially encourages submissions on the interface of IR and other disciplines, such as the Semantic Web, Databases, Computational Linguistics, Data Mining, Machine Learning, or Human Computer Interaction. Examples of topic of interest include (but are not limited to):

  • Data acquisition and processing (crawling, storage, and indexing)
  • Dealing with noisy, vague and incomplete data
  • Integration of data from multiple sources
  • Identification, resolution, and representation of entities (in documents and in queries)
  • Retrieval and ranking
  • Semantic query modeling (detecting, modeling, and understanding search intents)
  • Novel entity-oriented information access tasks
  • Interaction paradigms (natural language, keyword-based, and hybrid interfaces) and result representation
  • Test collections and evaluation methodology
  • Case studies and applications

We particularly encourage formal evaluation of approaches using previously established evaluation benchmarks: Semantic Search Challenge 2010, Semantic Search Challenge 2011, TREC Entity Search Track.

Keynote Speakers

  • Simple Models, Lots of Data: Mining semantics about entities using Web-Scale Data


    by Kaushik Chakrabarti, Microsoft Research

    SLIDES: Simple Models, Lots of Data - JIWES12 Keynote

    Abstract: Many areas in computer science like machine translation, speech recognition and computer vision are becoming more data-driven: statistical techniques that use simple models and use lots of data trump approaches that use complex models, deep algorithms or hand-coded rules. I believe that this is also true for mining semantics about entities. I will give some examples of such tasks like mining alternate names (aka "synonyms") of entities, finding descriptive phrases about entities, extracting semantic mentions of entities in documents and understanding attributes of entities and performing entity augmentation. I will discuss how we have used Web-scale data and simple, unsupervised algorithms to achieve high accuracy in these semantic tasks. This leads to several interesting research questions in statistical semantics and big data management.


  • The Lincoln Project: Building a Web-Scale Semantic Search Engine


    by John Shafer, Microsoft Research

    SLIDES: Lincoln Project - JIWES12 Keynote

    Abstract: All too frequently, entity search on the web is dismissed as needing nothing more than a tweaked version of an information-retrieval system, where entities are treated as documents and semantic search means bolting a few filter controls onto the side. To truly bring semantics to entity search requires an end-to-end upheaval of the entire search engine stack, from how rich structured catalogs are built and indexed, to the online query-processing system and user interface. I will speak about our experience in building from the ground up, Lincoln, a web-scale semantic search engine using a data feed of nearly 30 million products. I will present details of the entire system architecture with focus on the inner workings of the query-processing components. I will also touch upon back-end catalog creation, as well as our more recent efforts to extend the work beyond the world of entities and into the Wild Wild Web.

Organizers

Program Committee

  • Wojciech M. Barczynski (SAP Research)
  • Roi Blanco (Yahoo! Research)
  • Pablo Castells (Universidad Autónoma de Madrid)
  • Gianluca Demartini (University of Fribourg)
  • Michiel Hildebrand (VU University Amsterdam)
  • Arnd Christian König (Microsoft Research)
  • Oren Kurland (Technion, Israel Institute of Technology)
  • Edgar Meij (University of Amsterdam)
  • Einat Minkov (University of Haifa)
  • Kavitha Srinivas (IBM Research)
  • Martin Theobald (Max-Planck-Institut Informatik)
  • Sivan Yogev (IBM)
  • Ilya Zaihrayeu (Università degli Studi di Trento)

Submission and Proceedings

We invite submissions of
  • regular research papers (max. 6 pages),
  • position papers (max. 3 pages),
  • and demo descriptions (max. 3 pages).
All submissions will be reviewed by at least two program committee members, and will be assessed based on their novelty, technical quality, potential impact, and clarity of writing. Selection uses a standard double blind procedure. All accepted papers will be published as part of the SIGIR workshop proceedings and will be indexed in the ACM Digital Library. Please, submit in PDF format to:
EasyChair - jiwes2012
Using the ACM SIG Proceedings style (for LaTeX, use the "Option 2" style):
http://www.acm.org/sigs/publications/proceedings-templates

Best Contribution Award

The best contribution will receive an award ($300) sponsored by Yandex.


The participants of the workshop casted their votes:
The Best Contribution Award of JIWES 2012 goes to:

Hannah Bast, Florian Bäurle, Björn Buchhold, and Elmar Haussmann.

For their presentation and paper on:
A Case for Semantic Full-Text Search (position paper)(slides)

Contact

The organization committee can be reached at: jiwes.workshop@gmail.com

Workshop Series

Entity-oriented Workshop at SIGIR2011
Semantic Search Workshop at WWW2011 Semantic Search Challenge 2011
Semantic Search Workshop at WWW2010 Semantic Search Challenge 2010
Semantic Search Workshop at WWW2009
Semantic Search Workshop at ESWC2008