publications

2025

1. Conf

   CiteBART: Learning to Generate Citations for Local Citation Recommendation

   Ege Yiğit Çelik and Selma Tekir

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025

   DOI
2. J

   Recognition of Counterfactual Statements in Turkish

   Ali Acar and Selma Tekir

   ACM Trans. Asian Low-Resour. Lang. Inf. Process., Jan 2025

   Abs DOI

   Counterfactual statements are examples of causal reasoning as they describe events that did not happen and, optionally, those events’ consequences if they happened. SemEval-2020 introduces the counterfactual detection (CFD) task and shares an English dataset. Since then, a set of datasets has been released in English, German, and Japanese as part of Amazon product reviews. This work releases the first Turkish corpus of counterfactuals (TRCD). The data collection process is driven by a clue phrase list of counterfactuals, mainly in the form of verb inflections in Turkish. We use clue phrase-based filtering to collect sentences from the Turkish National Corpus (TNC). On the other hand, half of the collection is subject to random word filtering to avoid selection bias due to clue phrases. After the human annotation process with an Inter Annotator Agreement of 0.65, we have 5000 sentences, of which 12.8% contain counterfactual statements. Furthermore, we provide a comprehensive baseline of transformer-based models by testing the effect of clue phrases, cross-lingual performance comparisons using the available CFD datasets, and zero-shot cross-lingual classification experiments using fine-tuning on the different combinations of the existing datasets. The results confirm that TRCD is compatible with the other CFD datasets. Moreover, fine-tuning a Turkish-specific model (BERTurk) performs better than the multilingual alternatives (mBERT and XLM-R). BERTurk is more robust to clue phrase masking. This result emphasizes the importance of a language-specific tokenizer for contextual understanding, especially for low-resource languages. Finally, our qualitative analysis gives insights into errors by different models.

2024

1. ArXiv

   CiteBART: Learning to Generate Citations for Local Citation Recommendation

   Ege Yigit Çelik and Selma Tekir

   CoRR, Jan 2024

   DOI
2. Conf

   Çok Görevli BERT Modeli Üzerinde İyileştirmeler

   Mahmut Ağralı and Selma Tekir

   In 32nd Signal Processing and Communications Applications Conference, SIU 2024, Tarsus, Turkey, May 15-18, 2024, Jan 2024

   DOI
3. J

   Enrichment of Turkish question answering systems using knowledge graphs

   Okan Çiftçi, Fatih Soygazi, and Selma Tekir

   Turkish J. Electr. Eng. Comput. Sci., Jan 2024

   DOI
4. J

   Identifying promoter and enhancer sequences by graph convolutional networks

   Samet Tenekeci and Selma Tekir

   Computational Biology and Chemistry, Jan 2024

   Abs DOI

   Identification of promoters, enhancers, and their interactions helps understand genetic regulation. This study proposes a graph-based semi-supervised learning model (GCN4EPI) for the enhancer-promoter classification problem. We adopt a graph convolutional network (GCN) architecture to integrate interaction information with sequence features. Nodes of the constructed graph hold word embeddings of DNA sequences while edges hold the Enhancer-Promoter Interaction (EPI) information. By means of semi-supervised learning, much less data (16%) and time are needed in model training. Comparisons on a benchmark dataset of six human cell lines show that the proposed approach outperforms the state-of-the-art methods by a large margin (10% higher F1 score) and has the fastest training time (up to 3 times). Moreover, GCN4EPI’s performance on cross-cell line data is also better than the baselines (3% higher F1 score). Our qualitative analyses with graph explainability models prove that GCN4EPI learns from both text and graph structure. The results suggest that integrating interaction information with sequence features improves predictive performance and compensates for the number of training instances.

2023

1. Conf

   Quote Detection: A New Task and Dataset for NLP

   Selma Tekir, Aybüke Güzel, Samet Tenekeci, and 1 more author

   In Proceedings of the 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, May 2023

   Abs DOI

   Quotes are universally appealing. Humans recognize good quotes and save them for later reference. However, it may pose a challenge for machines. In this work, we build a new corpus of quotes and propose a new task, quote detection, as a type of span detection. We retrieve the quote set from Goodreads and collect the spans through a custom search on the Gutenberg Book Corpus. We measure unique vocabulary usage by a state-of-the-art language model and perform comparative statistical analysis against the Cornell Movie-Quotes Corpus. Furthermore, we run two types of baselines for quote detection: Conditional random field (CRF) and summarization with pointer-generator networks and Bidirectional and Auto-Regressive Transformers (BART). The results show that the neural sequence-to-sequence models perform substantially better than CRF. From the viewpoint of neural extractive summarization, quote detection seems easier than news summarization. Moreover, model fine-tuning on our corpus and the Cornell Movie-Quotes Corpus introduces incremental performance boosts.

2. ArXiv

   An End-to-End System for Reproducibility Assessment of Source Code Repositories via Their Readmes

   Eyüp Kaan Akdeniz, Selma Tekir, and Malik Nizar Asad Al Hinnawi

   CoRR, May 2023

   DOI

2022

1. J

   Asking the Right Questions to Solve Algebraic Word Problems

   Ege Yiğit Çelik, Zeynel Orulluoğlu, Rıdvan Mertoğlu, and 1 more author

   Turkish Journal of Electrical Engineering & Computer Sciences, May 2022

   DOI
2. J

   Gender Bias in Occupation Classification from the New York Times Obituaries

   Ceren Atik and Selma Tekir

   Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, May 2022

   DOI

2021

1. ArXiv

   A Survey On Neural Word Embeddings

   Erhan Sezerer and Selma Tekir

   CoRR, May 2021
2. ArXiv

   Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims

   Ipek Baris Schlicht, Erhan Sezerer, Selma Tekir, and 2 more authors

   CoRR, May 2021
3. Conf

   Performance Evaluation of BERT Vectors on Natural Language Inference Models

   Iskender Ulgen Ogul and Selma Tekir

   In 29th Signal Processing and Communications Applications Conference, SIU 2021, Istanbul, Turkey, June 9-11, 2021, May 2021

   DOI
4. J

   Incorporating Concreteness in Multi-Modal Language Models with Curriculum Learning

   Erhan Sezerer and Selma Tekir

   Applied Sciences, May 2021

   Abs DOI

   Over the last few years, there has been an increase in the studies that consider experiential (visual) information by building multi-modal language models and representations. It is shown by several studies that language acquisition in humans starts with learning concrete concepts through images and then continues with learning abstract ideas through the text. In this work, the curriculum learning method is used to teach the model concrete/abstract concepts through images and their corresponding captions to accomplish multi-modal language modeling/representation. We use the BERT and Resnet-152 models on each modality and combine them using attentive pooling to perform pre-training on the newly constructed dataset, which is collected from the Wikimedia Commons based on concrete/abstract words. To show the performance of the proposed model, downstream tasks and ablation studies are performed. The contribution of this work is two-fold: A new dataset is constructed from Wikimedia Commons based on concrete/abstract words, and a new multi-modal pre-training approach based on curriculum learning is proposed. The results show that the proposed multi-modal pre-training approach contributes to the success of the model.

5. J

   Author Reputation Measurement on Question and Answer Sites by the Classification of Author-Generated Content

   Erhan Sezerer, Samet Tenekeci, Ali Acar, and 2 more authors

   International Journal of Software Engineering and Knowledge Engineering, May 2021

   Abs DOI

   In the field of software engineering, practitioners’ share in the constructed knowledge cannot be underestimated and is mostly in the form of grey literature (GL). GL is a valuable resource though it is subjective and lacks an objective quality assurance methodology. In this paper, a quality assessment scheme is proposed for question and answer (Q&A) sites. In particular, we target stack overflow (SO) and stack exchange (SE) sites. We model the problem of author reputation measurement as a classification task on the author-provided answers. The authors’ mean, median, and total answer scores are used as inputs for class labeling. State-of-the-art language models (BERT and DistilBERT) with a softmax layer on top are utilized as classifiers and compared to SVM and random baselines. Our best model achieves 63.8% accuracy in binary classification in SO design patterns tag and 71.6% accuracy in SE software engineering category. Superior performance in SE software engineering can be explained by its larger dataset size. In addition to quantitative evaluation, we provide qualitative evidence, which supports that the system’s predicted reputation labels match the quality of provided answers.

2020

1. Chapter

   Deep Learning: Exemplar Studies in Natural Language Processing and Computer Vision

   Selma Tekir and Yalın Baştanlar

   May 2020

   DOI
2. J

   Estimating spatiotemporal focus of documents using entropy with PMI

   Damla Yaşar and Selma Tekir

   Turkish Journal of Electrical Engineering & Computer Sciences, May 2020

   Abs DOI

   Many text documents are spatiotemporal in nature, ie contents of a document can be mapped to a specific time period or location. For example, a news article about the French Revolution can be mapped to year 1789 as time and France as place. Identifying this time period and location associated with the document can be useful for various downstream applications such as document reasoning or spatiotemporal information retrieval. In this paper, temporal entropy with pointwise mutual information (PMI) is proposed to estimate the temporal focus of a document. PMI is used to measure the association of words with time expressions. Moreover, a word? s temporal entropy is considered as a weight to its association with a time point and a single time point with the highest overall score is chosen as the focus time of a document. The proposed method is generic in the sense that it can also be applied for spatial focus estimation of documents. In the case of spatial entropy with PMI, PMI is used to calculate the association between words and place entities. The effectiveness of our proposed methods for spatiotemporal focus estimation is evaluated on diverse datasets of text documents. The experimental evaluation confirms the superiority of our proposed temporal and spatial focus estimation methods.

3. Conf

   A Turkish Topic Modeling Dataset For Multi-label Classification of Movie Genre

   Elgun Jabrayilzade, Algin Poyraz Arslan, Hasan Para, and 3 more authors

   In 28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, October 5-7, 2020, May 2020

   DOI
4. Conf

   LGPSolver - Solving Logic Grid Puzzles Automatically

   Elgun Jabrayilzade and Selma Tekir

   In Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020, May 2020

   DOI
5. ArXiv

   Automatic Story Construction from News Articles in an Online Fashion

   Can and Selma Tekir

   CoRR, May 2020

2019

1. J

   Rule-Based Automatic Question Generation Using Semantic Role Labeling

   Onur Keklik, Tugkan Tuglular, and Selma Tekir

   IEICE Trans. Inf. Syst., May 2019

   DOI
2. J

   Sales History-based Demand Prediction using Generalized Linear Models

   Başar Özenboy and Selma Tekir

   Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, May 2019
3. Conf

   A Turkish Dataset for Gender Identification of Twitter Users

   Erhan Sezerer, Ozan Polatbilek, and Selma Tekir

   In Proceedings of the 13th Linguistic Annotation Workshop, LAW@ACL 2019, Florence, Italy, August 1, 2019, May 2019

   DOI
4. Conf

   Gender Prediction from Turkish Tweets with Neural Networks

   Erhan Sezerer, Ozan Polatbilek, and Selma Tekir

   In 27th Signal Processing and Communications Applications Conference, SIU 2019, Sivas, Turkey, April 24-26, 2019, May 2019

   DOI
5. ArXiv

   Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features

   Erhan Sezerer, Ozan Polatbilek, and Selma Tekir

   CoRR, May 2019

2018

1. Conf

   Gender Prediction From Tweets With Convolutional Neural Networks: Notebook for PAN at CLEF 2018

   Erhan Sezerer, Ozan Polatbilek, Sevgili, and 1 more author

   In Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum, Avignon, France, September 10-14, 2018, May 2018
2. Conf

   Doğruluk problemi için veri kümesi hazırlanması

   Arif Kürşat Karabayır, Ozan Onur Tek, Özgür Fırat Çınar, and 1 more author

   In Proceedings of the 12th Turkish National Software Engineering Symposium, UYMS 2018, Istanbul, Turkey, September 10-12, 2018, May 2018

2017

1. Conf

   A Relativistic Opinion Mining Approach to Detect Factual or Opinionated News Sources

   Erhan Sezerer and Selma Tekir

   In Big Data Analytics and Knowledge Discovery - 19th International Conference, DaWaK 2017, Lyon, France, August 28-31, 2017, Proceedings, May 2017

   DOI
2. Conf

   A News Chain Evaluation Methodology along with a Lattice-based Approach for News Chain Construction

   Mustafa Toprak, Özkahraman, and Selma Tekir

   In Proceedings of the 2017 Workshop: Natural Language Processing meets Journalism, NLPmJ@EMNLP, Copenhagen, Denmark, September 7, 2017, May 2017

   DOI
3. Conf

   N-Hance at SemEval-2017 Task 7: A Computational Approach using Word Association for Puns

   Sevgili, Nima Ghotbi, and Selma Tekir

   In Proceedings of the 11th International Workshop on Semantic Evaluation, SemEval@ACL 2017, Vancouver, Canada, August 3-4, 2017, May 2017

   DOI

2016

1. Conf

   Sosyal Cizgeler Icin Arama Motoru Gelistirilmesi

   Erman Yafay and Selma Tekir

   In Proceedings of the 10th Turkish National Software Engineering Symposium, UYMS 2016, Canakkale, Turkey, October 24-26, 2016, May 2016

2015

1. Conf

   Bir Platform Oyununa Kullanıcı Performansı Temelinde Yapay Zeka Uyarlaması

   Sercan Türkmen, Hilmi Yalin Mungan, and Selma Tekir

   In Proceedings of the 9th Turkish National Software Engineering Symposium, UYMS 2015, Yasar University, Izmir, Turkey, September, 9-11, 2015, May 2015

2012

1. CACM

   Reading CS classics

   Selma Tekir

   Commun. ACM, May 2012

   DOI
2. J

   Geodesic Distances for Clustering Linked Text Data

   Selma Tekir, Florian Mansmann, and Daniel Keim

   Journal of Artificial Intelligence and Soft Computing Research, May 2012
3. Conf

   Overt Information Operations During Peacetime

   Selma Tekir

   In ECIW 2012 11th European Conference on Information Warfare and Security, May 2012
4. Conf

   Recent Cyberwar Spectrum and its Analysis

   Rabia Aslanoglu and Selma Tekir

   In ECIW 2012 11th European Conference on Information Warfare and Security, May 2012

2011

1. Conf

   Geodesic distances for web document clustering

   Selma Tekir, Florian Mansmann, and Daniel A. Keim

   In Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2011, part of the IEEE Symposium Series on Computational Intelligence 2011, April 11-15, 2011, Paris, France, May 2011

   DOI