Skip to main content
Presentation
PLW Tutorial: Processing Narratives by Means of Action Languages​
Philadelphi Logic Week (2019)
  • Yuliya Lierler
Abstract
The tutorial explains the design of a narrative understanding tool Text2Alm. System Text2Alm uses an action language ALM to perform inferences on complex interactions of events described in narratives. The methodology used to implement the Text2Alm was originally outlined by Lierler, Inclezan, and Gelfond in 2017. Text2Alm relies on a conglomeration of resources and techniques from two distinct fields of artificial intelligence, namely, natural language processing and knowledge representation and reasoning. The tutorial will also present the results on the effectiveness of system Text2Alm measured by its ability to correctly answer questions from the bAbI tasks published by Facebook Research in 2015. This tool matched or exceeded the performance of state-of-the-art machine learning methods in six of the seven tested tasks.
Disciplines
Publication Date
June 4, 2019
Location
Philadelphia, USA
Citation Information
Yuliya Lierler. "PLW Tutorial: Processing Narratives by Means of Action Languages​" Philadelphi Logic Week (2019)
Available at: http://works.bepress.com/yuliya_lierler/89/