Publications with Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/6
Browse
81 results
Search Results
Publication Open Access User interface paradigms for visually authoring mid-air gestures: a survey and a provocation(CEUR-WS, 2014) Department of Media and Visual Arts; Department of Computer Engineering; Department of Media and Visual Arts; Department of Computer Engineering; Baytaş, Mehmet Aydın; Yemez, Yücel; Özcan, Oğuzhan; Faculty Member; Faculty Member; College of Social Sciences and Humanities; College of Engineering; N/A; N/A; 12532Gesture authoring tools enable the rapid and experiential prototyping of gesture-based interfaces. We survey visual authoring tools for mid-air gestures and identify three paradigms used for representing and manipulating gesture information: graphs, visual markup languages and timelines. We examine the strengths and limitations of these approaches and we propose a novel paradigm to authoring location-based mid-air gestures based on space discretization.Publication Open Access The noisy channel mode for unsupervised word sense disambiguation(Massachusetts Institute of Technology (MIT) Press, 2010) Department of Computer Engineering; Department of Computer Engineering; Yüret, Deniz; Yatbaz, Mehmet Ali; Faculty Member; PhD Student; College of Engineering; 179996; 192506We introduce a generative probabilistic model, the noisy channel model, for unsupervised word sense disambiguation. In our model, each context C is modeled as a distinct channel through which the speaker intends to transmit a particular meaning S using a possibly ambiguous word W. To reconstruct the intended meaning the hearer uses the distribution of possible meanings in the given context P(S|C) and possible words that can express each meaning P(W|S). We assume P(W|S) is independent of the context and estimate it using WordNet sense frequencies. The main problem of unsupervised WSD is estimating context-dependent P(S|C) without access to any sense-tagged text. We show one way to solve this problem using a statistical language model based on large amounts of untagged text. Our model uses coarse-grained semantic classes for S internally and we explore the effect of using different levels of granularity on WSD performance. The system outputs fine-grained senses for evaluation, and its performance on noun disambiguation is better than most previously reported unsupervised systems and close to the best supervised systems.Publication Open Access GestAnalytics: experiment and analysis tool for gesture-elicitation studies(Association for Computing Machinery (ACM), 2017) Department of Computer Engineering; Department of Computer Engineering; Buruk, Oğuz Turan; Özcan, Oğuzhan; Faculty Member; KU Arçelik Research Center for Creative Industries (KUAR) / KU Arçelik Yaratıcı Endüstriler Uygulama ve Araştırma Merkezi (KUAR); College of Engineering; N/A; 12532Gesture-elicitation studies are common and important studies for understanding user preferences. In these studies, researchers aim at extracting gestures which are desirable by users for different kinds of interfaces. During this process, researchers have to manually analyze many videos which is a tiring and a time consuming process. Although current tools for video analysis provide annotation opportunity and features like automatic gesture analysis, researchers still need to (1) divide videos into meaningful pieces, (2) manually examine each piece, (3) match collected user data with these, (4) code each video and (5) verify their coding. These processes are burdensome and current tools do not aim to make this process easier and faster. To fill this gap, we developed “GestAnalytics” with features of simultaneous video monitoring, video tagging and filtering. Our internal pilot tests show that GestAnalytics can be a beneficial tool for researchers who practice video analysis for gestural interfaces.Publication Open Access Tree-stack LSTM in transition based dependency parsing(Association for Computational Linguistics (ACL), 2018) Department of Computer Engineering; N/A; Department of Computer Engineering; Yüret, Deniz; Faculty Member; College of Engineering; Graduate School of Sciences and Engineering; 179996; N/AWe introduce tree-stack LSTM to model state of a transition based parser with recurrent neural networks. Tree-stack LSTM does not use any parse tree based or hand-crafted features, yet performs better than models with these features. We also develop new set of embeddings from raw features to enhance the performance. There are 4 main components of this model: stack's σ-LSTM, buffer's βLSTM, actions' LSTM and tree-RNN. All LSTMs use continuous dense feature vectors (embeddings) as an input. Tree-RNN updates these embeddings based on transitions. We show that our model improves performance with low resource languages compared with its predecessors. We participate in CoNLL 2018 UD Shared Task as the”KParse” team and ranked 16th in LAS, 15th in BLAS and BLEX metrics, of 27 participants parsing 82 test sets from 57 languages.Publication Open Access Multiple shape correspondence by dynamic programming(Wiley, 2014) Sahillioğlu, Y.; Department of Computer Engineering; Department of Computer Engineering; Yemez, Yücel; Faculty Member; College of EngineeringWe present a multiple shape correspondence method based on dynamic programming, that computes consistent bijective maps between all shape pairs in a given collection of initially unmatched shapes. As a fundamental distinction from previous work, our method aims to explicitly minimize the overall distortion, i.e., the average isometric distortion of the resulting maps over all shape pairs. We cast the problem as optimal path finding on a graph structure where vertices are maps between shape extremities. We exploit as much context information as possible using a dynamic programming based algorithm to approximate the optimal solution. Our method generates coarse multiple correspondences between shape extremities, as well as denser correspondences as by-product. We assess the performance on various mesh sequences of (nearly) isometric shapes. Our experiments show that, for isometric shape collections with non-uniform triangulation and noise, our method can compute relatively dense correspondences reasonably fast and outperform state of the art in terms of accuracy.Publication Open Access Observation of the correlations between pair wise interaction and functional organization of the proteins, in the protein ınteraction network of saccaromyces cerevisiae(World Academy of Science, Engineering and Technology (WASET), 2008) Haliloğlu, T.; Department of Computer Engineering; Department of Chemical and Biological Engineering; Department of Computer Engineering; Department of Chemical and Biological Engineering; Tunçbağ, Nurcan; Keskin, Özlem; Faculty Member; College of Engineering; N/A; 26605Understanding the cell's large-scale organization is an interesting task in computational biology. Thus, protein-protein interactions can reveal important organization and function of the cell. Here, we investigated the correspondence between protein interactions and function for the yeast. We obtained the correlations among the set of proteins. Then these correlations are clustered using both the hierarchical and biclustering methods. The detailed analyses of proteins in each cluster were carried out by making use of their functional annotations. As a result, we found that some functional classes appear together in almost all biclusters. On the other hand, in hierarchical clustering, the dominancy of one functional class is observed. In brief, from interaction data to function, some correlated results are noticed about the relationship between interaction and function which might give clues about the organization of the proteins.Publication Open Access On the importance of hidden bias and hidden entropy in representational efficiency of the Gaussian-Bipolar Restricted Boltzmann Machines(Elsevier, 2018) Department of Computer Engineering; Department of Computer Engineering; Isabekov, Altynbek; Erzin, Engin; Faculty Member; College of Engineering; N/A; 34503In this paper, we analyze the role of hidden bias in representational efficiency of the Gaussian-Bipolar Restricted Boltzmann Machines (GBPRBMs), which are similar to the widely used Gaussian-Bernoulli RBMs. Our experiments show that hidden bias plays an important role in shaping of the probability density function of the visible units. We define hidden entropy and propose it as a measure of representational efficiency of the model. By using this measure, we investigate the effect of hidden bias on the hidden entropy and provide a full analysis of the hidden entropy as function of the hidden bias for small models with up to three hidden units. We also provide an insight into understanding of the representational efficiency of the larger scale models. Furthermore, we introduce Normalized Empirical Hidden Entropy (NEHE) as an alternative to hidden entropy that can be computed for large models. Experiments on the MNIST, CIFAR-10 and Faces data sets show that NEHE can serve as measure of representational efficiency and gives an insight on minimum number of hidden units required to represent the data.Publication Open Access HotRegion: a database of predicted hot spot clusters(Oxford University Press (OUP), 2012) N/A; Department of Computer Engineering; Department of Chemical and Biological Engineering; Department of Computer Engineering; Department of Chemical and Biological Engineering; Çukuroğlu, Engin; Gürsoy, Attila; Keskin, Özlem; PhD Student; Faculty Member; Graduate School of Sciences and Engineering; College of Engineering; N/A; 8745; 26605Hot spots are energetically important residues at protein interfaces and they are not randomly distributed across the interface but rather clustered. These clustered hot spots form hot regions. Hot regions are important for the stability of protein complexes, as well as providing specificity to binding sites. We propose a database called HotRegion, which provides the hot region information of the interfaces by using predicted hot spot residues, and structural properties of these interface residues such as pair potentials of interface residues, accessible surface area (ASA) and relative ASA values of interface residues of both monomer and complex forms of proteins. Also, the 3D visualization of the interface and interactions among hot spot residues are provided.Publication Open Access Sparse: Koç University graph-based parsing system for the CoNLL 2018 shared task(Association for Computational Linguistics (ACL), 2018) Department of Computer Engineering; N/A; Department of Computer Engineering; Yüret, Deniz; Önder, Berkay Furkan; Gümeli, Can; Faculty Member; College of Engineering; Graduate School of Sciences and Engineering; 179996; N/A; N/AWe present SParse, our Graph-Based Parsing model submitted for the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (Zeman et al., 2018). Our model extends the state-of-the-art biaffine parser (Dozat and Manning, 2016) with a structural meta-learning module, SMeta, that combines local and global label predictions. Our parser has been trained and run on Universal Dependencies datasets (Nivre et al., 2016, 2018) and has 87.48% LAS, 78.63% MLAS, 78.69% BLEX and 81.76% CLAS (Nivre and Fang, 2017) score on the Italian-ISDT dataset and has 72.78% LAS, 59.10% MLAS, 61.38% BLEX and 61.72% CLAS score on the Japanese-GSD dataset in our official submission. All other corpora are evaluated after the submission deadline, for whom we present our unofficial test results.Publication Open Access Mühendis gözüyle ekolojik tahribata bir örnek: BP çevre felaketi(Yapı Kredi Yayınları, 2019) Department of Computer Engineering; Department of Computer Engineering; Yobas, Mümine Banu; Teaching Faculty; College of Engineering