WWW 2018

Latent Semantics for the Web (LSW)


Held in conjunction with ACM WWW’18, held April 2018 in Lyon, France

Latent Semantics for the Web (LSW)

Introduction

Understanding the semantics of Web content is at the core of many applications, ranging from Web search, news aggregation and machine translation to personal assistant services such as Amazon Echo, Cortana, Siri, and Google Home. Latent Semantics utilizes a rich suite of information retrieval and machine learning techniques that capture meaning through powerful statistical neural network-based methods like word2vec and node2vec. Recently, such emerging semantic models have achieved state-of-the-art results in several predictive applications (e.g. recommendation, node classification, knowledge graph completion) relevant not just to the broader World Wide Web research community, but also allied communities such as Semantic Web, data mining and natural language processing. In the LSW workshop, we explore the convergence of latent semantics (LS) models and the Web. We explore several aspects of LS models that are particularly relevant to the Web, namely
• Novel methods, including embedding methods, that take into account the specific properties of the Web (e.g., link structure, multimedia content…)
• Evaluation of LS methods, especially in a Web context
• Intersection of LS models with traditional ontological semantics
• Reasoning about such models in a rigorous way
•Extending the scope of these models with techniques such as zero-shot learning and transfer learning.

Format

We are looking forward to a highly interactive workshop with participants from a wide range of backgrounds, from researchers to application builders, and from academia to industry. Researchers with an interdisciplinary interest in exploring synergies between various areas, especially graph (including knowledge graph) embeddings, World Wide Web and deep neural networks, are especially invited to participate and submit papers. In addition to oral presentations selected from submitted papers, we will have poster sessions, and an invited talk.

CFP

Short and long papers are solicited for the following set of non-exhaustive topics:

Theory, Algorithms and Methods:


• Novel Latent Semantic (LS) and embedding models, especially for diverse data such as webpages, RDF graphs, and ontologies
• Theoretical foundations of LS models
• Novel algorithms for representing and embedding knowledge graphs
• Novel methods for Knowledge graph completion
• Novel synergies for combining LS models with graphical models like Probabilistic Soft Logic (PSL) and Markov Logic Networks (MLNs)
• Innovative and efficient methods for querying LS models
• Theoretically grounded methods for evaluating LS models

Applications


• Web search
• Question answering
• Personalization
• Data Mining
• User interfaces and visualization
• Semantic recommendations
• Link prediction
• Node classification
• Instance matching/Entity resolution

Experiments, Systems and Data


• Novel datasets, especially datasets acquired through, or useful for evaluating, Web-specific LS models
• Novel methodologies, concerning both evaluations and data curation/collection
• Experimental results using existing methods, including negative results of interest
• Descriptions of best practices, case studies, lessons learned, and features

We will also accept a small number of vision, opinion and position papers that provide discussions on challenges and roadmaps (for hybrid systems, and emerging semantic models).

All papers should be formatted according to the latest ACM double-column conference format also used for the main research track at WWW. All papers will be peer reviewed, single-blinded. Authors whose papers are accepted to the workshop will have the opportunity to participate in a poster session, and some set may also be chosen for oral presentation. Long papers should not exceed than 8 pages, and short papers should not exceed 4 pages, including all references. The accepted papers will be published in the WWW18 Satellite Proceedings and will not be considered archival.

We are using the EasyChair system for submissions. If you would like to make a submission, please enter as an author and then select the name of the workshop (Latent Semantics for the Web) to submit papers and be sure to select the correct name as other workshops may also be listed, along with other satellite tracks!

Please email any enquiries to Mayank Kejriwal and cc Michael Cochez

Key Dates

Dec. 17: First call for papers/Submissions Open
Feb. 5 (Extended): Workshop papers due
Feb. 26: Notification of accepted papers
April 23: Workshop

Accepted Papers

TBD

Schedule

TBD

Keynote Speaker

TBD

Organization

Chair

Previous Editions

The previous edition of LSW (then titled Hybrid Statistical Semantic Understanding and Emerging Semantics or HSSUES) was held in conjunction with the International Semantic Web Conference (ISWC) in Vienna, Austria in October, 2017.