One of the emerging trends of information needs in search engine is using vertical search intent. For example, a user may want to find a restaurant near her current location; another user may want to follow the recent development of a breaking event such as the earthquake in Japan. Recent studies reveal that vertical search engines start attracting more and more attention. Thus, designing effective ranking functions for vertical search has become practically important to improve users' search experience. However, in many verticals, the meaning of relevance is domain-specific and usually consists of multiple well-defined aspects. Thus, we have identified a list of challenging research issues in the field of relevance for vertical search, which mainly fall into two categories, including (1) how to learn an effective ranking model considering multi-facets relevance; (2) how to build effective business model in the context of specific vertical search systems. This workshop is dedicated to presentations and discussions on relevance for vertical search. The workshop will bring together researchers from IR, ML, NLP, and other areas of computer and information science who are working on or interested in this area, and provide a forum for them to identify the issues and the challenges, to share their latest research results, to express a diverse range of opinions about this topic, and to discuss future directions. 

Call for Papers

Topics of interests include, but are not limited to:
  • Vertical domain content representation and analysis
  • Vertical domain query analysis and modeling
  • Retrieval models and ranking
  • Architectures and scalability of vertical search engine
  • Users and interactive IR in vertical search
  • Evaluation for vertical search
  • Applications (e.g., digital libraries, enterprise search, commercial search, genomics IR, legal IR, patent search, etc.)

Important Dates
 Submission Fri, Jan 31, 2014, 23:59 Hawaii time (HST)
 Notification Tue, Feb 4
 Camera-ready Wed, Feb 12
 Workshop          Mon, Apr 7


Submission Procedure

Submissions should be made electronically in PDF format via the electronic submission system available at:


If you do not have an EasyChair account, please register first. Once you get the log-in information by email, log into the system as an author. Enter all the required data about your submission and finally upload your contributed paper in PDF format.

This workshop is meant to be a venue to dissemination of early, possibly incomplete or tentative results. We’d like to let the authors know that workshop papers are publications. Any paper published by the ACM, IEEE, etc. which can be properly cited constitutes research which must be considered in judging the novelty of a WWW submission, whether the published paper was in a conference, journal, or workshop. Therefore, any paper previously published as part of a WWW workshop must be referenced and suitably extended with new content to qualify as a new submission to the Research Track at the WWW conference.

The workshop paper should occupy no more than six pages, including the abstract, references, and appendices.


Program

Program for Vertical Search Relevance Workshop (April 7 Monday Morning)

Session 1: 9:00-10:30am

Title

Speaker

9:00-9:30am (30 mins)

Local Search Relevance

Changsung Kang, Yahoo Labs

9:30-10:00am (30 mins)

Leibiz: an entity matching framework

Bo Zhao, Microsoft Research

10:00-10:30am (30 mins)

A quest to Discoverable, Relevant, and Lovable E-commerce search

Marcus Chan and Tzu-Chiang Liou, Yahoo Taiwan

Coffee Break: 10:30-11:00

Session 2: 11:00am-12:40pm

11:00am-11:50am (50 mins)

Keynote: Mass Information Extraction: Building Deep Vertical Search Engines

Kevin Chang, UIUC

11:50am-12:15pm (25 mins)

Representation discovery for e-commerce products

Vidit Jain, Yahoo Labs

12:15-12:40pm, (25 mins)

Seed Selection for Domain-Specific Search

Pattisapu Nikhil, IIIT



Organizers

Workshop Chairs

Hongbo Deng, Yahoo! Labs

Jiang Bian, Microsoft Research

Neel Sundaresan, eBay Research Labs

Yi Chang, Yahoo! Labs