CoMeT | <%=title %>
Collaborative Management of Talks Hello! sign in or register
Bookmark Talks, Share with Friends, and We Recommend More!
Advanced Search
Home
Calendar
Series
Speaker
Groups
Connections
 
 
 
 
Talk Detail
Posted: peterb on  Apr 15 10:11:41 AM
Title: Contextual Parameter Generation for Knowledge Graph Link Prediction  
Speaker:
Otilia Stretcu
Ph.D. Student, Machine Learning Department, Carnegie Mellon University
Sponsor: Carnegie Mellon University  >  School of Computer Science
Series: Artificial Intelligence Lunch Seminar
Date: Apr 16, 2019 12:00 PM - 1:00 PM
URL:
Location: NSH 3305
Groups Posted: Intelligent Systems Program PAWS Group Semantic Web Group 
Bookmarked by:  chirayu
Detail:

 

Abstract: Knowledge graph link prediction is the task of inferring missing relationships between entities in a knowledge graph. It can be seen as a form of question answering, where given a question consisting of an entity and a relation (e.g., “Shakespeare” and “bornIn”), we are tasked with predicting the most likely answer entity (e.g., “England”). Recent methods have focused on inferring answers by learning entity and relation embeddings. For example, the current state-of-the-art, ConvE, stacks the question entity and relation embeddings together and uses a convolutional neural network to predict the answer entity. However, we argue that entities and relations model different kinds of information and thus, integrating them in this way does not represent a meaningful inductive bias for the model. Therefore, we instead propose to treat relations as the “context” in which question entities are interpreted and transformed to produce answer entities. Concretely, we use relation embeddings to generate the parameters of a model operating over entity embeddings, which in turn produces a distribution over possible answers. This proposed model outperforms all existing methods by a significant margin on several established datasets, thus establishing the new state-of-the-art for this problem, while at the same time reducing training time by up to 98%.

--

Interest Area: Computer & Information Science & Engineering
 
 
People Who Bookmarked This Talk, Also Bookmarked
 
 
Export
RSS Feed: RSS 2.0
ATOM Feed: Atom
iCalendar: iCal
Share: Bookmark and Share
 
Google Calendar:
 
 
 
 
CoMeT Blog
©2009-2019 CoMeT - Supported by Google Grant
School of Information Sciences, University of Pittsburgh, 135 North Bellefield Avenue, Pittsburgh, PA 15260
Real Time Web Analytics