Şükrü Ozan

Şükrü Ozan

Recent studies in DNA sequence classification have leveraged sophisticated machine learning techniques, achieving notable accuracy in categorizing complex genomic data. Among these, methods such as k-mer counting have proven effective in distinguishing sequences from varied species like chimpanzees, dogs, and humans, becoming a staple in contemporary genomic research. However, these approaches often demand extensive computational resources, posing a challenge in terms of scalability and efficiency. Addressing this issue, our study introduces a novel adaptation of Jiang et al.'s compressor-based, parameter-free classification method, specifically tailored for DNA sequence analysis. This innovative approach utilizes a variety of compression algorithms, such as Gzip, Brotli, and LZMA, to efficiently process and classify genomic sequences. Not only does this method align with the current state-of-the-art in terms of accuracy, but it also offers a more resource-efficient alternative to traditional machine learning methods. Our comprehensive evaluation demonstrates the proposed method's effectiveness in accurately classifying DNA sequences from multiple species. We present a detailed analysis of the performance of each algorithm used, highlighting the strengths and limitations of our approach in various genomic contexts. Furthermore, we discuss the broader implications of our findings for bioinformatics, particularly in genomic data processing and analysis. The results of our study pave the way for more efficient and scalable DNA sequence classification methods, offering significant potential for advancements in genomic research and applications.

D. Emre Taşar, Şükrü Ozan, M. Fatih Akca et al.

Text classification problem is a very broad field of study in the field of natural language processing. In short, the text classification problem is to determine which of the previously determined classes the given text belongs to. Successful studies have been carried out in this field in the past studies. In the study, Bidirectional Encoder Representations for Transformers (BERT), which is a frequently preferred method for solving the classification problem in the field of natural language processing, is used. By solving classification problems through a single model to be used in a chatbot architecture, it is aimed to alleviate the load on the server that will be created by more than one model used for solving more than one classification problem. At this point, with the masking method applied during the estimation of a single BERT model, which was created for classification in more than one subject, the estimation of the model was provided on a problem-based basis. Three separate data sets covering different fields from each other are divided by various methods in order to complicate the problem, and classification problems that are very close to each other in terms of field are also included in this way. The dataset used in this way consists of five classification problems with 154 classes. A BERT model containing all classification problems and other BERT models trained specifically for the problems were compared with each other in terms of performance and the space they occupied on the server.

Umut Özdil, Büşra Arslan, D. Emre Taşar et al.

In this study, a natural language processing-based (NLP-based) method is proposed for the sector-wise automatic classification of ad texts created on online advertising platforms. Our data set consists of approximately 21,000 labeled advertising texts from 12 different sectors. In the study, the Bidirectional Encoder Representations from Transformers (BERT) model, which is a transformer-based language model that is recently used in fields such as text classification in the natural language processing literature, was used. The classification efficiencies obtained using a pre-trained BERT model for the Turkish language are shown in detail.

Şükrü Ozan

How can a text corpus stored in a customer relationship management (CRM) database be used for data mining and segmentation? In order to answer this question we inherited the state of the art methods commonly used in natural language processing (NLP) literature, such as word embeddings, and deep learning literature, such as recurrent neural networks (RNN). We used the text notes from a CRM system which are taken by customer representatives of an internet ads consultancy agency between years 2009 and 2020. We trained word embeddings by using the corresponding text corpus and showed that these word embeddings can not only be used directly for data mining but also be used in RNN architectures, which are deep learning frameworks built with long short term memory (LSTM) units, for more comprehensive segmentation objectives. The results prove that structured text data in a CRM can be used to mine out very valuable information and any CRM can be equipped with useful NLP features once the problem definitions are properly built and the solution methods are conveniently implemented.

Şükrü Ozan, D. Emre Taşar

In this study, we aim to find a method to auto-tag sentences specific to a domain. Our training data comprises short conversational sentences extracted from chat conversations between company's customer representatives and web site visitors. We manually tagged approximately 14 thousand visitor inputs into ten basic categories, which will later be used in a transformer-based language model with attention mechanisms for the ultimate goal of developing a chatbot application that can produce meaningful dialogue. We considered three different state-of-the-art models and reported their auto-tagging capabilities. We achieved the best performance with the bidirectional encoder representation from transformers (BERT) model. Implementation of the models used in these experiments can be cloned from our GitHub repository and tested for similar auto-tagging problems without much effort.

Şükrü Ozan, Leonardo Obinna Iheme

This work presents a practical solution to the problem of call center agent malpractice. A semi-supervised framework comprising of non-linear power transformation, neural feature learning and k-means clustering is outlined. We put these building blocks together and tune the parameters so that the best performance was obtained. The data used in the experiments is obtained from our in-house call center. It is made up of recorded agent-customer conversations which have been annotated using a convolutional neural network based segmenter. The methods provided a means of tuning the parameters of the neural network to achieve a desirable result. We show that, using our proposed framework, it is possible to significantly reduce the malpractice classification error of a k-means-only clustering model which would serve the same purpose. Additionally, by presenting the amount of silence per call as a key performance indicator, we show that the proposed system has enhanced agents performance at our call center since deployment.

Şükrü Ozan

Detailed statistical analysis of call center recordings is critical in the customer relationship management point of view. With the recent advances in artificial intelligence, many tasks regarding the calculation of call statistics are now performed automatically. This work proposes a neural network framework where the aim is to correctly identify audio segments and classify them as either customer or agent sections. Accurately identifying these sections gives a fair metric for evaluating agents' performances. We inherited the convolutional recurrent neural network (CRNN) architecture commonly used for such problems as music genre classification. We also tested the same architecture's performance, where the previous class information and the gender information of speakers are also added to the training data labels. We saw that CRNN could generalize the training data and perform well on validation data for this problem with and without the gender information. Moreover, even the training was performed using Turkish speech samples; the trained network was proven to achieve high accuracy for call center recordings in other languages like German and English.

D. Emre Taşar, Şükrü Ozan, Umut Özdil et al.

The problem of categorizing short speech sentences according to their semantic features with high accuracy is a subject studied in natural language processing. In this study, a data set created with samples classified in 46 different categories was used. Examples consist of sentences taken from chat conversations between a company's customer representatives and the company's website visitors. The primary purpose is to automatically tag questions and requests from visitors in the most accurate way for 46 predetermined categories for use in a chat application to generate meaningful answers to the questions asked by the website visitors. For this, different BERT models and one GPT-2 model, pre-trained in Turkish, were preferred. The classification performances of the relevant models were analyzed in detail and reported accordingly.