Arzucan Özgür

Arzucan Özgür

Associate Professor @ Department of Computer Engineering, Bogazici University

I am a faculty member in the Department of Computer Engineering at Bogazici University, and co-director of TABI (Text Analytics and Bioinformatics) Lab. I'm also a member of the AILAB. My research is at the intersection of bioinformatics and natural language processing with the goal of developing algorithms for processing and understanding both natural (human) languages and the languages encoded in biological molecular sequences.

Natural Language Processing Bioinformatics Text Mining Machine Learning Information Extraction Turkish Language Processing
Email Google Scholar DBLP CV
Short Bio

I joined the Department of Computer Engineering at Bogazici University in 2011. Prior to that I worked in the Faculty of Computer and Informatics at Istanbul Technical University between 2010-2011. I received my Ph.D. degree in Computer Science and Engineering from the University of Michigan, Ann Arbor, USA in 2010. I hold an M.S. degree and a B.S. degree in Computer Engineering from Bogazici University.

Recent News

2022

Gokce Uludogan presented "Exploiting Pretrained Biochemical Language Models for Targeted Drug Design" at ECCB 2022 in Barcelona, Spain. The paper is published in the Bioinformatics journal.

2023

Arzucan Ozgur serves in the Organizing Committee of RECOMB 2023, which took place in Istanbul between 14-19 April 2023.

2022

Arzucan Ozgur serves as Vice Chair for the IAPR Technical Committee on Pattern Recognition for Bioinformatics and Digital Health between 2022-2024.

2022

New paper co-authored by Merve Unlu Menevse, Yusufcan Manav, Ebru Arisoy, and Arzucan Ozgur entitled "A Framework for Automatic Generation of Spoken Question-Answering Data" is accepted to the Findings of EMNLP 2022.

2022

Saziye Betul Ozates successfully defended her PhD thesis entitled "Deep Learning-based Dependency Parsing for Turkish".

Funded Projects

Utilizing Digital Technology for Social Cohesion

Utilizing Digital Technology for Social Cohesion, Positive Messaging and Peace by Boosting Collaboration, Exchange and Solidarity. The project is led by the Hrant Dink Foundation (HDV) and is a collaboration between HDV, Sabanci University, and Bogazici University.

NLP Hate Speech Detection Social Media
European Union - EuropeAid 2021-2024
Chemical Language Processing for Target-based Drug Design

Developing chemical language processing methods for target-based drug design using deep learning approaches.

Bioinformatics Drug Design Deep Learning
TUBITAK 1001 2019-2022
A Deep Learning based Turkish Dependency Parser

Developing a deep learning based dependency parser for Turkish language.

NLP Turkish Deep Learning Parsing
TUBITAK 1005 2018-2019
Contextual Text Mining from the Biomedical Scientific Literature

Developing text mining techniques to automatically extract biologically important information such as relationships between biomolecules from scientific publications.

Text Mining Bioinformatics Information Extraction
European Commission, FP7 Marie Curie Career Integration Grant 2012-2016

Selected Publications

Google Scholar DBLP

Exploiting pretrained biochemical language models for targeted drug design

Gokce Uludogan, Elif Ozkirimli, Kutlu Ulgen, Nilgun Karali, Arzucan Ozgur

Bioinformatics, Volume 38, Issue Supplement_2, Pages ii155–ii161, 2022
Paper
Cluster-based mention typing for named entity disambiguation

Arda Celebi, Arzucan Ozgur

Natural Language Engineering, 28(1), 1-37, 2022
Paper
Resources for Turkish dependency parsing: Introducing the BOUN treebank and the BoAT annotation tool

Utku Turk, Furkan Atmaca, Saziye Betul Ozates, Gozde Berk, Seyyit Talha Bedir, Abdullatif Koksal, Balkiz Ozturk Basaran, Tunga Gungor, Arzucan Ozgur

Language Resources and Evaluation, 56(1), pp. 259-307, 2022
Paper
A Hybrid Deep Dependency Parsing Approach Enhanced With Rules and Morphology: A Case Study for Turkish

Saziye Betul Ozates, Arzucan Ozgur, Tunga Gungor, Balkiz Ozturk Basaran

IEEE Access, vol. 10, pp. 93867-93886, 2022
Paper
Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary Tasks

Saziye Betul Ozates, Arzucan Ozgur, Tunga Gungor, Ozlem Cetinoglu

Findings of the Association for Computational Linguistics: NAACL 2022, pp. 1159-1171
Paper
A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts

Mustafa Melih Mutlu, Arzucan Ozgur

ACL 2022: Student Research Workshop, pages 467–472, Dublin, Ireland
Paper
Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution

Yi Huang, Buse Giledereli, Abdullatif Koksal, Arzucan Ozgur, Elif Ozkirimli

EMNLP 2021, pages 8153–8161, Online and Punta Cana, Dominican Republic
Paper
ChemBoost: A Chemical Language Based Approach for Protein - Ligand Binding Affinity Prediction

Riza Ozcelik, Hakime Ozturk, Arzucan Ozgur, Elif Ozkirimli

Molecular Informatics, 40, 2000212, 2021
Paper

Software & Tools

VAPUR

A Search Engine for Related Protein-Compound Pairs in COVID-19 Literature

Visit
WarmMolGen

A Tool for Protein Target-based Chemical Molecule Generation

Visit
TULAP

The Turkish Language Processing Platform

Visit
BIOSSES

Biomedical Sentence Similarity Estimation System

Visit
Hashtag Segmentation Tool

Tool for segmenting hashtags in social media text

Visit
PHISTO

Pathogen-Host Interaction Search Tool

Visit

Students

Current PhD Students

  • Gonul Ayci (Co-advise with Pinar Yolum)
  • Melih Barsbey (Co-advise with Taylan Cemgil)
  • Nuriye Ozlem Ozcan Simsek (Co-advise with Fikret Gurgen)
  • Burak Suyunu
  • Gokce Uludogan
  • Merve Unlu Menevse (Co-advise with Ebru Arisoy)
  • Enes Taylan

Current MS Students

  • Omer Ak
  • Nur Bengisu Cam
  • Omer Faruk Cavas
  • Sadullah Gultekin (Co-advise with Pinar Yanardag)
  • Musa Nuri Ihtiyar
  • Berke Kavak
  • Burak Can Koban
  • Yusufcan Manav (Co-advise with Ebru Arisoy)
  • Busra Oguzoglu
  • Bugrahan Sahin
  • Cansu Damla Yilmaz

PhD Alumni

  • Ilknur Karadeniz 2019
    Ontology-based Entity Tagging and Normalization in the Biomedical Domain
    Assistant Professor at Isik University
  • Hakime Ozturk 2019
    Text-based Machine Learning for Modelling Drug-Target Interactions
    Researcher at DKFZ (German Cancer Research Center), Heidelberg
  • Arda Celebi 2020
    Utilizing Weakly-Supervised Learning for Hashtag Segmentation and Named Entity Disambiguation
    CTO and Co-Founder of VireUp
  • Saziye Betul Ozates 2022
    Deep Learning-based Dependency Parsing for Turkish
    Post-doctoral researcher at Koc University, Istanbul

Selected MS Alumni

  • Bedirhan Caldir 2022
    Predicting intracellular functions of proteins from amino acid sequences using language processing methods
  • Atif Emre Yuksel 2022
    Hate Speech Detection in Turkish News using a Transformer-based Model Enhanced with Linguistic Features
  • Riza Ozcelik 2022
    Biomolecular language processing for drug-target affinity prediction
  • Abdullatif Koksal 2021
    Datasets and transformer models for cross-lingual relation classification
  • Gokce Uludogan 2021
    Targeted drug design with warm start

Teaching

Current Courses

CMPE549 - Bioinformatics

Past Courses

CMPE 321 - Introduction to Database Systems
CMPE 484 - Introduction to Bioinformatics and Computational Genomics
CMPE 150 - Introduction to Computing
CMPE 220 - Discrete Computational Structures
CMPE 493 - Introduction to Information Retrieval
CMPE 561 - Natural Language Processing
CMPE 59K - Information Retrieval
CMPE 59H - Bioinformatics

Contact

Department of Computer Engineering, Bogazici University, 34342 Bebek, Istanbul, Turkey

Office: BM 18

+90 212 359 7226

arzucan.ozgur@boun.edu.tr

Links

TABI Lab
AILAB
Department of Computer Engineering
Bogazici University