Aykut Koc's research while affiliated with Bilkent University and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (65)
The beam propagation method (BPM) can be viewed as a chain of alternating convolutions and multiplications, as filtering operations alternately in the space and frequency domains or as multiplication operations sandwiched between linear canonical or fractional Fourier transforms. These structures provide alternative models of inhomogeneous media an...
Hate speech against individuals or communities with different backgrounds is a major problem in online social networks. The domain of hate speech has spread to various topics, including race, religion, and gender. Although there are many efforts for hate speech detection in different domains and languages, the effects of gender identity are not sol...
Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other areas. Although the attention mechanism enhances the model performances significantly, its quadratic complexity p...
The processing of legal texts has been developing as an emerging field in natural language processing (NLP). Legal texts contain unique jargon and complex linguistic attributes in vocabulary, semantics, syntax, and morphology. Therefore, the development of text simplification (TS) methods specific to the legal domain is of paramount importance for...
Natural language processing (NLP) technologies and applications in legal text processing are gaining momentum. Being one of the most prominent tasks in NLP, named-entity recognition (NER) can substantiate a great convenience for NLP in law due to the variety of named entities in the legal domain and their accentuated importance in legal documents....
We propose bidirectional imparting or BiImp, a generalized method for aligning embedding dimensions with concepts during the embedding learning phase. While preserving the semantic structure of the embedding space, BiImp makes dimensions interpretable, which has a critical role in deciphering the black-box behavior of word embeddings. BiImp separat...
Word embeddings have become important building blocks that are used profoundly in natural language processing (NLP). Despite their several advantages, word embeddings can unintentionally accommodate some gender- and ethnicity-based biases that are present within the corpora they are trained on. Therefore, ethical concerns have been raised since wor...
Graphs signal processing successfully captures high-dimensional data on non-Euclidean domains by using graph signals defined on graph vertices. However, data sources on each vertex can also continually provide time-series signals such that graph signals on each vertex are now time-series signals. Joint time-vertex Fourier transform (JFT) and the as...
Utilizing signal processing tools in deep learning models has been drawing increasing attention. Fourier transform (FT), one of the most popular signal processing tools, is employed in many deep learning models. Transformer-based sequential input processing models have also started to make use of FT. In the existing FNet model, it is shown that rep...
Natural language processing (NLP) based approaches have recently received attention for legal systems of several countries. It is of interest to study the wide variety of legal systems that have so far not received any attention. In particular, for the legal system of the Republic of Turkey, codified in Turkish, no works have been published. We fir...
Linear canonical transforms (LCTs) are extensively used in many areas of science and engineering with many applications, which requires a satisfactory discrete implementation. Recently, hyperdifferential operators have been proposed as a novel way of defining the discrete LCT (DLCT). Here we first focus on improving the accuracy of this approach by...
We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics, and social sciences. In particular, we introduce a sentiment analysis framework in multi-label setting as it obeys Plutchik's wheel of emotions. We introduce a novel dynamic weighti...
On the Euclidean domains of classical signal processing, linking of signal samples to underlying coordinate structures is straightforward. While graph adjacency matrices totally define the quantitative associations among the underlying graph vertices, a major problem in graph signal processing is the lack of explicit association of vertices with an...
Graph signal processing has recently received considerable attention. Several concepts, tools, and applications in signal processing such as filtering, transforming, and sampling have been extended to graph signal processing. One such extension is the optimal filtering problem. The minimum mean-squared error estimate of an original graph signal can...
Being one of the most common empirical regularities, the Zipf’s law for word frequencies is a power law relation between word frequencies and frequency ranks of words. We quantitatively study semantic uncertainty of words through non-point distribution-based word embeddings and reveal the Zipfian regularities. Uncertainty of a word can increase due...
Signal scaling is a fundamental operation of practical importance in which a signal is made wider or narrower along the coordinate direction(s). Scaling, also referred to as magnification or zooming, is complicated for signals of a discrete variable since it cannot be accomplished simply by moving the signal values to new coordinate points. Most pr...
![Fig. 1: Plutchik's [5] wheel of emotions.](profile/Selim-Yilmaz-6/publication/343904122/figure/fig1/AS:928987199049728@1598499216140/Plutchiks-5-wheel-of-emotions_Q320.jpg)
We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis framework in multi-label setting as it obeys Plutchik wheel of emotions. We introduce a novel dynamic weighting...
On the Euclidean domains of classical signal processing, linking of signal samples to the underlying coordinate structure is straightforward. While graph adjacency matrices totally define the quantitative associations among the underlying graph vertices, a major problem in graph signal processing is the lack of explicit association of vertices with...
As a ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words, but the vectors corresponding to the words are only meaningful relative to each other. Neither the vector nor its dimension...
Objective:
Balanced steady-state free precession (bSSFP) imaging suffers from banding artifacts in the presence of magnetic field inhomogeneity. The purpose of this study is to identify an efficient strategy to reconstruct banding-free bSSFP images from multi-coil multi-acquisition datasets.
Method:
Previous techniques either assume that a naïve...
The fractional Fourier transform is of importance in several areas of signal processing with many applications including optical signal processing. Deploying it in practical applications requires discrete implementations, and therefore defining a discrete fractional Fourier transform (DFRT) is of considerable interest. We propose an operator theory...
Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep embedding learning by using a multi-task learning framework, in which the hierarchical labels (coarse and fine label...
The classical phase retrieval problem is the recovery of a constrained image from the magnitude of its Fourier transform. Although there are several well-known phase retrieval algorithms, including the hybrid input-output (HIO) method, the reconstruction performance is generally sensitive to initialization and measurement noise. Recently, deep neur...
Classical phase retrieval problem is the recovery of a constrained image from the magnitude of its Fourier transform. Although there are several well-known phase retrieval algorithms including the hybrid input-output (HIO) method, the reconstruction performance is generally sensitive to initialization and measurement noise. Recently, deep neural ne...
Linear canonical transforms (LCTs) are of importance in many areas of science and engineering with many applications. Therefore a satisfactory discrete implementation is of considerable interest. Although there are methods that link the samples of the input signal to the samples of the linear canonical transformed output signal, no widely-accepted...
This study aims to increase the performance of word embeddings by proposing a new weighting scheme for co-occurrence counting. The idea behind this new family of weights is to overcome the disadvantage of distant appearing word pairs, which are indeed semantically close, while representing them in the co-occurrence counting. For high-resource langu...
We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
Using phase detection in Surface Plasmon Resonance (SPR) sensing
has potential improvements to the conventional intensity detection based SPR. Other
than the phase detection and intensity detection based SPR in the visible range
of the spectrum, employing SPR sensing principles in the infrared range by the
use of silicon has also some promising adv...
As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words but the vector corresponding to the words are only meaningful relative to each other. Neither the vector nor its dimensions...
Recent advances in large-scale image and video analysis have empowered the potential capabilities of visual surveillance systems. In particular, deep learning-based approaches bring in substantial benefits in solving certain computer vision problems such as fine-grained object recognition. Here, the authors mainly concentrate on classification and...
Linear canonical transforms (LCTs) are of importance in several areas of signal processing with many applications. Therefore a satisfactory discrete implementation is of considerable interest. Although there are methods that link the samples of the input signal to the samples of the linear canonical transformed output signal, no widely-accepted def...
Signal scaling is a fundamental operation of practical importance in which a signal is enlarged or shrunk in the coordinate direction(s). Scaling or magnification is not trivial for signals of a discrete variable since the signal values may not fall onto the discrete coordinate points. One approach is to consider the discretely-spaced values as the...
This study revisits
the problem of maximizing the performance of mathematical word representations
for a given task. It is aimed to improve performance in analogy and similarity
tasks by suggesting innovative weights instead of the counting weights used
conventionally in counting-based methods of generating word representations
(adding the statisti...
Wide-field interferometric microscopy is a highly sensitive, label-free, and low-cost biosensing imaging technique capable of visualizing individual biological nanoparticles such as viral pathogens and exosomes. However, further resolution enhancement is necessary to increase detection and classification accuracy of subdiffraction-limited nanoparti...
Fine-grained visual categorization has recently received great attention as the volumes of labeled datasets for classification of specific objects, such as cars, bird species, and air-crafts, have been increasing. The availability of large datasets led to significant performance improvements in several vision-based classification tasks. Visual clas...
Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks. Word embeddings are substantially successful in capturing semantic relations among words, so a meaningful semantic struct...
A central limitation of multiple-acquisition magnetic resonance imaging (MRI) is the degradation in scan efficiency as the number of distinct datasets grows. Sparse recovery techniques can alleviate this limitation via randomly undersampled acquisitions. A frequent sampling strategy is to prescribe for each acquisition a different random pattern dr...
Fine-grained visual categorization has recently received great attention as the volumes of the labelled datasets for classification of specific objects, such as cars, bird species, and aircrafts, have been increasing. The collection of large datasets has helped vision based classification approaches and led to significant improvements in performanc...
Sparse recovery aims to reconstruct signals that are sparse in a linear transform domain from a heavily underdetermined set of measurements. The success of sparse recovery relies critically on the knowledge of transform domains that give compressible representations of the signal of interest. Here we consider two- and three-dimensional images, and...
Word embedding, which is usually used in the literature especially for English, is a technique to associate each word to a mathematical vector representation under which some structural or semantic relations hold. There are some Turkish application of this technique. Despite being designed according to English, it is also satisfactory for Turkish....
In this work, we focus on the problem of infrared (IR) object classification by dividing the object appearance space hierarchically with a binary decision tree structure. Specially designed features of the object appearances make the binary decisions at each node of the tree. These features are extracted using a fully connected deep neural network....
Citations
... Most deep learning approaches use the deep architectural background as the foundation rather than calculating distance metrics in a new representation space of the data. As a result, distance-based methods are one of the most fascinating areas of deep learning [36,[55][56][57][58][59][60], while DML decreases the distance between dissimilar samples. DML increases the distance between similar samples, which is directly correlated to the distance between samples [61,62]. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/501269711331328-1496523420383_Q64/Erhan-Gundogdu.jpg)
... Since the proposed weight favors the distant relations more than the original weight, it is more suitable for Turkish semantic structure. Indeed, we have a similar study for English in Yücesoy and Koç, (2017) and that study revealed that the performance of the proposed weight increases the performance of the word embedding for analogy test by approximately 2%. When these two results are considered together, it might be possible to conclude that the proposed weight is more suitable to Turkish semantic relations than the English relations. ...
... Primarily based on NLP techniques, there is an explosion of interest in developing algorithms for high-level legal technology applications [5]- [9]. These include legal judgement forecasting [10]- [22], legal topic classification [9], [23], [24], legal text summarization [8], [25], legal question&answer systems [26]- [30], gender debiasing in legal corpora [31], information and feature extraction from legal contracts and documents [32]- [35], legal named-entity recognition (legal-NER) [1], [36]- [38], and court opinion generation [39]. Following the advancements in machine learning and NLP-based computational law, standardized benchmarks have also emerged [6]. ...
Reference: Unsupervised Simplification of Legal Texts
... Furthermore, they show that biased word embeddings still cluster according to their bias even after debiasing operation [9]. Finally, since language models' bias affects the language models' fairness, there are also studies tackling the problem in the legal domain [19]. ...
... However, it does not use the negative directions of the vectors. In a later work [166] they used the positive and negative both direction of embedding vectors by changing the loss function of Glove and Word2Vec [96] vectors. Both the positive and negative directions are aligned to different concepts. ...
... More special matrices lead to some other known integral transforms, e.g., Fresnel transform, chirp functions etc. Various applications of LCT have been realized in the field of electromagnatic, acoustic and other wave propagation problems. As mentioned in [9], LCT is known by other terminolgy as well such as quadractic phase integral [1], generalized Huygens integral [14], generalized Fresnel transform [7], [12] etc. Recently, in [13], the authors have studied certain mapping properties of LCT and the associated pseudo-differential operators in a variant of Schwartz space. ...
... However, Turkish pronouns do not contain any gender information. This problem is tackled in [27], and gender-specific words for measuring and debiasing Turkish word embeddings are proposed. For instance, ...
... Event-related tweets are classified by using URLs that link to news sources [12]. Pre-trained language models are also studied to detect topics in Turkish microblogs [34]. However, these studies do not target the task of event-related microblog retrieval. ...
Reference: Event-related microblog retrieval in Turkish
... In solving multilingual problems using a deep learning approach, Ref. [31] developed a deep learning approach using XLM-RoBERTa, Bidirectional Recurrent Neural Networks (Bi-RNNs), and Bidirectional Long Short-Term Memory (LSTM) to perform multi-label emotion classification on 100 types of languages without detecting its language. The authors of [12] used Global Vectors (GloVe) as word embeddings and input them into RNN-LSTM to create a basic model on an English dataset and to convert other languages into English using Neural Machine Translation (NMT) before the model could perform sentiment analysis on multilingual texts. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/933074971942915-1599473817891_Q64/Selim-Yilmaz-6.jpg)
... Several pre-trained language models were evaluated on CAUD and Transformer based models were the most efficient. • For predicting the rulings of the Turkish Constitutional Court and Courts of Appeal, Mumcuoğlu et al. [175] proposed an NLP approach using ML classifiers like SVM, RF, and Decision Trees (DT) with deep learning methods like LSTM and BLSTM. ...
