• Publications
  • Influence
Semantic Structure and Interpretability of Word Embeddings
TLDR
Dense word embeddings are substantially successful in capturing semantic relations among words, so a meaningful semantic structure must be present in the respective vector spaces. Expand
  • 44
  • 3
  • PDF
Imparting Interpretability to Word Embeddings while Preserving Semantic Structure.
TLDR
We introduce an additive modification to the objective function of the embedding learning algorithm that encourages word embedding vectors that are semantically related to a predefined concept to take larger values along a specified dimension, while leaving the original semantic learning mechanism mostly unaffected. Expand
  • 5
  • PDF
Imparting Interpretability to Word Embeddings
TLDR
We introduce an additive modification to the objective function of the embedding learning algorithm that encourages word embedding vectors of words that are semantically related a predefined concept to take larger values along a specified dimension, while leaving the original semantic learning mechanism mostly unaffected. Expand
  • 6
Resource-aware event triggered distributed estimation over adaptive networks
TLDR
We propose a novel algorithm for distributed processing applications constrained by the available communication resources using diffusion strategies that achieves up to a 3 fold reduction in the communication load over the network, while delivering a comparable performance with respect to the state of the art. Expand
  • 4
  • PDF
Generating Semantic Similarity Atlas for Natural Languages
TLDR
We leverage a recently proposed word embedding based method to generate a language similarity atlas for 76 different languages around the world. Expand
  • 3
Distributed adaptive filtering with reduced communication load
  • Ihsan Utlu, S. Kozat
  • Computer Science
  • 24th European Signal Processing Conference…
  • 1 August 2016
TLDR
We propose novel algorithms for distributed processing in applications constrained by available communication resources, using diffusion strategies that achieve up to three orders-of-magnitude reduction in communication load on the network, while delivering equal performance with respect to the state of the art. Expand
  • 1
  • PDF
Communication efficient distributed estimation
  • Ihsan Utlu, S. Kozat
  • Computer Science
  • 24th Signal Processing and Communication…
  • 16 May 2016
TLDR
In this paper, we consider the problem of distributed estimation over adaptive networks with reduced load on communication resources. Expand