Koc Lab is a research group at Bilkent University focusing on Natural Language Processing research. Some research on graph signal processing is also going on.

News

20.10.2021

In the paper “Semantic Change Detection with Gaussian Word Embeddings” published at IEEE Transactions on Audio, Speech and Language Processing, KocLab has developed the first Gaussian word embedding (w2g)-based approach to the problem of lexical semantic change detection. The proposed method reached high rankings (including the first rank at one of the two sub-tasks) at the SemEval 2020 Task 1, which is the standardized evaluation framework of the field.

12.07.2021

KocLab has published a pioneering paper on Natural Language Processing (NLP) in law with a specific emphasis on the Turkish legal system. The paper entitled “Natural Language Processing in Law: Prediction of outcomes in the Higher Courts of Turkey” has been published at Information Processing and Management and addresses the Turkish Legal System in a comprehensive manner and develops NLP techniques for the legal system of the Republic of Turkey.

03.06.2021

KocLab’s new paper entitled “Graph Signal Processing: Vertex Multiplication” has been published at IEEE Signal Processing Letters, where we made a fundamental contribution to graph signal processing (GSP) by introducing an important and fundamental GSP operator.

19.05.2021

We and our collaborators have published the paper entitled “Optimal fractional Fourier filtering for graph signals” at IEEE Transactions on Signal Processing, where we studied Wiener filtering in the graph signal processing (GSP) domain.

19.01.2021

Our new paper “Zipfian regularities in non-point word representations”, where we revealed a new Zipfian regularity for semantic breadth, has been published at Information Processing & Management. Code and more details are available at our Github repository.

04.11.2020

Our new paper  has been published at Digital Signal Processing.

17.08.2020

02.07.2020

Dr. Koç has been elevated to Senior Member level by IEEE.

You can access the code for Imparting Interpretability to Word Embeddings While Preserving Semantic Structure from here.

02.07.2020

09.06.2020

Our new paper has been published at Natural Language Engineering of Cambridge University Press.