DECISIVE ANALYTICS Corporation Employees Presented at the 52nd Annual Meeting of the Association for Computational Linguistics and The FrameNet Workshop

ARLINGTON, Va., July 22, 2014 /PRNewswire/ -- DECISIVE ANALYTICS Corporation employees, Peter David, Alison Smith, Timothy Hawes and Meredith Myers presented on a variety of technical topics at this year's Annual Meeting of the Association for Computational Linguistics (ACL 2014) and the FrameNet Workshop that immediately followed. They gave a presentation and also presented a poster during the workshop sessions of the ACL Conference and a separate presentation during the FrameNet workshop.

ACL 2014 covered a broad spectrum of disciplines working towards enabling intelligent systems to interact with humans using natural language, to understanding computational and other linguistic properties of language, and to enhancing human-human communication through services such as speech recognition, automatic translation, information retrieval, text summarization, and information extraction.

The main topic that DECISIVE ANALYTICS' employee's discussed during their presentation and poster at ACL 2014 was interactive visualization for hierarchical topic models.

Alison, Meredith and Tim's presentation focused on a case study for interacting with a large repository of documents that have been analyzed using DAC's patented topic modeling capability.  Essentially the problem is that existing algorithms for understanding large collections of documents often produce output that is nearly as difficult and time consuming to interpret as reading each of the documents themselves. Our patented topic modeling capability is a text understanding algorithm that discovers the "topics" or themes within a collection of documents. Tools based on topic modeling become increasingly complex as the number of topics required to best represent the collection increases. In this presentation, the group presented Hierarchie, an interactive visualization that adds structure to large topic models, making them approachable and useful to an end user. The chosen use case demonstrated Hierarchie's ability to analyze a diverse document set regarding a trending news topic.

Peter David and Timothy Hawes also presented at the FrameNet Workshop 2, held in conjunction with ACL 2014 on June 29th in Baltimore. This one-day workshop covered current projects using FrameNet and issues to be addressed in scaling FrameNet up into a widely used resource.  Peter and Tim provided an overview of how DECISIVE ANALYTICS have developed a reasoning engine around FrameNet to automatically extract and identify roles and relationships from large repositories of text, as well as how it can be leveraged to perform semantic search. 

About DECISIVE ANALYTICS Corporation:

DECISIVE ANALYTICS Corporation is an employee-owned system engineering company headquartered in Arlington, VA.  Founded in 1996, DECISIVE ANALYTICS core ideology is to bring together highly motivated individuals to form an organization that provides superior, innovative technical contributions to all endeavors in which it participates.  DECISIVE ANALYTICS delivers industry-leading products and services to commercial businesses, the Department of Defense, the Intelligence Community, and a wide range of other government agencies.  DECISIVE ANALYTICS is consistently ranked among the Best Places to work, the 50 Fastest Growing Technology firms in Virginia, and the 500 Fastest Growing Companies in North America. DECISIVE ANALYTICS also has offices in Huntsville, AL; Colorado Springs, CO; and Jeffersonville, IN.  For more information, please visit www.dac.us.

SOURCE DECISIVE ANALYTICS Corporation



RELATED LINKS
http://www.dac.us

More by this Source


Custom Packages

Browse our custom packages or build your own to meet your unique communications needs.

Start today.

 

PR Newswire Membership

Fill out a PR Newswire membership form or contact us at (888) 776-0942.

Learn about PR Newswire services

Request more information about PR Newswire products and services or call us at (888) 776-0942.