I
Ivan Titov
Researcher at University of Edinburgh
Publications - 182
Citations - 15172
Ivan Titov is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Parsing & Machine translation. The author has an hindex of 48, co-authored 172 publications receiving 11367 citations. Previous affiliations of Ivan Titov include Saarland University & University of Geneva.
Papers
More filters
Book ChapterDOI
Modeling Relational Data with Graph Convolutional Networks
Michael Sejr Schlichtkrull,Thomas Kipf,Peter Bloem,Rianne van den Berg,Ivan Titov,Ivan Titov,Max Welling,Max Welling +7 more
TL;DR: It is shown that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.
Posted Content
Modeling Relational Data with Graph Convolutional Networks
Michael Sejr Schlichtkrull,Thomas Kipf,Peter Bloem,Rianne van den Berg,Ivan Titov,Ivan Titov,Max Welling,Max Welling +7 more
TL;DR: Relational Graph Convolutional Networks (R-GCNets) as discussed by the authors are related to a recent class of neural networks operating on graphs, and are developed specifically to deal with the highly multi-relational data characteristic of realistic knowledge bases.
Proceedings ArticleDOI
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
TL;DR: It is found that the most important and confident heads play consistent and often linguistically-interpretable roles and when pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, it is observed that specialized heads are last to be pruned.
Posted Content
Modeling Online Reviews with Multi-grain Topic Models
Ivan Titov,Ryan McDonald +1 more
TL;DR: This paper presents a novel framework for extracting ratable aspects of objects from online user reviews and argues that multi-grain models are more appropriate for this task since standard models tend to produce topics that correspond to global properties of objects rather than aspects of an object that tend to be rated by a user.
Proceedings Article
A Joint Model of Text and Aspect Ratings for Sentiment Summarization
Ivan Titov,Ryan McDonald +1 more
TL;DR: A statistical model is proposed which is able to discover corresponding topics in text and extract textual evidence from reviews supporting each of these aspect ratings, a fundamental problem in aspect-based sentiment summarization.