PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1309.1129

Analysing Quality of English-Hindi Machine Translation Engine Outputs Using Bayesian Classification

This paper considers the problem for estimating the quality of machine translation outputs which are independent of human intervention and are generally addressed using machine learning techniques.There are various measures through which a machine learns translations quality. Automatic Evaluation metrics produce good co-relation at corpus level but cannot produce the same results at the same segment or sentence level. In this paper 16 features are extracted from the input sentences and their translations and a quality score is obtained based on Bayesian inference produced from training data.

arXiv:1309.0999

Minutiae Based Thermal Face Recognition using Blood Perfusion Data

This paper describes an efficient approach for human face recognition based on blood perfusion data from infra-red face images. Blood perfusion data are characterized by the regional blood flow in human tissue and therefore do not depend entirely on surrounding temperature. These data bear a great potential for deriving discriminating facial thermogram for better classification and recognition of face images in comparison to optical image data. Blood perfusion data are related to distribution of blood vessels under the face skin. A distribution of blood vessels are unique for each person and as a set of extracted minutiae points from a blood perfusion data of a human face should be unique for that face. There may be several such minutiae point sets for a single face but all of these correspond to that particular face only. Entire face image is partitioned into equal blocks and the total number of minutiae points from each block is computed to construct final vector. Therefore, the size of the feature vectors is found to be same as total number of blocks considered. For classification, a five layer feed-forward backpropagation neural network has been used. A number of experiments were conducted to evaluate the performance of the proposed face recognition system with varying block sizes. Experiments have been performed on the database created at our own laboratory. The maximum success of 91.47% recognition has been achieved with block size 8X8.

arXiv:1309.0309

A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification

Many efforts have been devoted to develop alternative methods to traditional vector quantization in image domain such as sparse coding and soft-assignment. These approaches can be split into a dictionary learning phase and a feature encoding phase which are often closely connected. In this paper, we investigate the effects of these phases by separating them for video-based action classification. We compare several dictionary learning methods and feature encoding schemes through extensive experiments on KTH and HMDB51 datasets. Experimental results indicate that sparse coding performs consistently better than the other encoding methods in large complex dataset (i.e., HMDB51), and it is robust to different dictionaries. For small simple dataset (i.e., KTH) with less variation, however, all the encoding strategies perform competitively. In addition, we note that the strength of sophisticated encoding approaches comes not from their corresponding dictionaries but the encoding mechanisms, and we can just use randomly selected exemplars as dictionaries for video-based action classification.

arXiv:1307.3043

A two-layer Conditional Random Field for the classification of partially occluded objects

Conditional Random Fields (CRF) are among the most popular techniques for image labelling because of their flexibility in modelling dependencies between the labels and the image features. This paper proposes a novel CRF-framework for image labeling problems which is capable to classify partially occluded objects. Our approach is evaluated on aerial near-vertical images as well as on urban street-view images and compared with another methods.

arXiv:1305.7345

Algebraic Properties of Qualitative Spatio-Temporal Calculi

Qualitative spatial and temporal reasoning is based on so-called qualitative calculi. Algebraic properties of these calculi have several implications on reasoning algorithms. But what exactly is a qualitative calculus? And to which extent do the qualitative calculi proposed meet these demands? The literature provides various answers to the first question but only few facts about the second. In this paper we identify the minimal requirements to binary spatio-temporal calculi and we discuss the relevance of the according axioms for representation and reasoning. We also analyze existing qualitative calculi and provide a classification involving different notions of a relation algebra.

arXiv:1305.6143공식 코드 · Papers with Code

Fast and accurate sentiment classification using an enhanced Naive Bayes model

We have explored different methods of improving the accuracy of a Naive Bayes classifier for sentiment analysis. We observed that a combination of methods like negation handling, word n-grams and feature selection by mutual information results in a significant improvement in accuracy. This implies that a highly accurate and fast sentiment classifier can be built using a simple Naive Bayes model that has linear training and testing time complexities. We achieved an accuracy of 88.80% on the popular IMDB movie reviews dataset.

arXiv:1304.0102

Entanglement Zoo II: Examples in Physics and Cognition

We have recently presented a general scheme enabling quantum modeling of different types of situations that violate Bell's inequalities. In this paper, we specify this scheme for a combination of two concepts. We work out a quantum Hilbert space model where 'entangled measurements' occur in addition to the expected 'entanglement between the component concepts', or 'state entanglement'. We extend this result to a macroscopic physical entity, the 'connected vessels of water', which maximally violates Bell's inequalities. We enlighten the structural and conceptual analogies between the cognitive and physical situations which are both examples of a nonlocal non-marginal box modeling in our classification.

arXiv:1304.0100

Entanglement Zoo I: Foundational and Structural Aspects

We put forward a general classification for a structural description of the entanglement present in compound entities experimentally violating Bell's inequalities, making use of a new entanglement scheme that we developed recently. Our scheme, although different from the traditional one, is completely compatible with standard quantum theory, and enables quantum modeling in complex Hilbert space for different types of situations. Namely, situations where entangled states and product measurements appear ('customary quantum modeling'), and situations where states and measurements and evolutions between measurements are entangled ('nonlocal box modeling', 'nonlocal non-marginal box modeling'). The role played by Tsirelson's bound and marginal distribution law is emphasized. Specific quantum models are worked out in detail in complex Hilbert space within this new entanglement scheme.

arXiv:1211.2190

Efficient Monte Carlo Methods for Multi-Dimensional Learning with Classifier Chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance - at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest- performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

arXiv:1009.5358

Task-Driven Dictionary Learning

Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience and signal processing. For signals such as natural images that admit such sparse representations, it is now well established that these models are well suited to restoration tasks. In this context, learning the dictionary amounts to solving a large-scale matrix factorization problem, which can be done efficiently with classical optimization tools. The same approach has also been used for learning features from data for other purposes, e.g., image classification, but tuning the dictionary in a supervised way for these tasks has proven to be more difficult. In this paper, we present a general formulation for supervised dictionary learning adapted to a wide variety of tasks, and present an efficient algorithm for solving the corresponding optimization problem. Experiments on handwritten digit classification, digital art identification, nonlinear inverse image problems, and compressed sensing demonstrate that our approach is effective in large-scale settings, and is well suited to supervised and semi-supervised classification, as well as regression tasks for data that admit sparse representations.

arXiv:1309.5843

Sentiment Analysis: How to Derive Prior Polarities from SentiWordNet

Assigning a positive or negative score to a word out of context (i.e. a word's prior polarity) is a challenging task for sentiment analysis. In the literature, various approaches based on SentiWordNet have been proposed. In this paper, we compare the most often used techniques together with newly proposed ones and incorporate all of them in a learning framework to see whether blending them can further improve the estimation of prior polarity scores. Using two different versions of SentiWordNet and testing regression and classification models across tasks and datasets, our learning approach consistently outperforms the single metrics, providing a new state-of-the-art approach in computing words' prior polarity for sentiment analysis. We conclude our investigation showing interesting biases in calculated prior polarity scores when word Part of Speech and annotator gender are considered.

arXiv:1309.5823

A Kernel Classification Framework for Metric Learning

Learning a distance metric from the given training samples plays a crucial role in many machine learning tasks, and various models and optimization algorithms have been proposed in the past decade. In this paper, we generalize several state-of-the-art metric learning methods, such as large margin nearest neighbor (LMNN) and information theoretic metric learning (ITML), into a kernel classification framework. First, doublets and triplets are constructed from the training samples, and a family of degree-2 polynomial kernel functions are proposed for pairs of doublets or triplets. Then, a kernel classification framework is established, which can not only generalize many popular metric learning methods such as LMNN and ITML, but also suggest new metric learning methods, which can be efficiently implemented, interestingly, by using the standard support vector machine (SVM) solvers. Two novel metric learning methods, namely doublet-SVM and triplet-SVM, are then developed under the proposed framework. Experimental results show that doublet-SVM and triplet-SVM achieve competitive classification accuracies with state-of-the-art metric learning methods such as ITML and LMNN but with significantly less training time.

arXiv:1309.5427

Latent Fisher Discriminant Analysis

Linear Discriminant Analysis (LDA) is a well-known method for dimensionality reduction and classification. Previous studies have also extended the binary-class case into multi-classes. However, many applications, such as object detection and keyframe extraction cannot provide consistent instance-label pairs, while LDA requires labels on instance level for training. Thus it cannot be directly applied for semi-supervised classification problem. In this paper, we overcome this limitation and propose a latent variable Fisher discriminant analysis model. We relax the instance-level labeling into bag-level, is a kind of semi-supervised (video-level labels of event type are required for semantic frame extraction) and incorporates a data-driven prior over the latent variables. Hence, our method combines the latent variable inference and dimension reduction in an unified bayesian framework. We test our method on MUSK and Corel data sets and yield competitive results compared to the baseline approach. We also demonstrate its capacity on the challenging TRECVID MED11 dataset for semantic keyframe extraction and conduct a human-factors ranking-based experimental evaluation, which clearly demonstrates our proposed method consistently extracts more semantically meaningful keyframes than challenging baselines.

arXiv:1309.5226

DGT-TM: A freely Available Translation Memory in 22 Languages

The European Commission's (EC) Directorate General for Translation, together with the EC's Joint Research Centre, is making available a large translation memory (TM; i.e. sentences and their professionally produced translations) covering twenty-two official European Union (EU) languages and their 231 language pairs. Such a resource is typically used by translation professionals in combination with TM software to improve speed and consistency of their translations. However, this resource has also many uses for translation studies and for language technology applications, including Statistical Machine Translation (SMT), terminology extraction, Named Entity Recognition (NER), multilingual classification and clustering, and many more. In this reference paper for DGT-TM, we introduce this new resource, provide statistics regarding its size, and explain how it was produced and how to use it.

arXiv:1309.5223

JRC EuroVoc Indexer JEX - A freely available multi-label categorisation tool

EuroVoc (2012) is a highly multilingual thesaurus consisting of over 6,700 hierarchically organised subject domains used by European Institutions and many authorities in Member States of the European Union (EU) for the classification and retrieval of official documents. JEX is JRC-developed multi-label classification software that learns from manually labelled data to automatically assign EuroVoc descriptors to new documents in a profile-based category-ranking task. The JEX release consists of trained classifiers for 22 official EU languages, of parallel training data in the same languages, of an interface that allows viewing and amending the assignment results, and of a module that allows users to re-train the tool on their own document collections. JEX allows advanced users to change the document representation so as to possibly improve the categorisation result through linguistic pre-processing. JEX can be used as a tool for interactive EuroVoc descriptor assignment to increase speed and consistency of the human categorisation process, or it can be used fully automatically. The output of JEX is a language-independent EuroVoc feature vector lending itself also as input to various other Language Technology tasks, including cross-lingual clustering and classification, cross-lingual plagiarism detection, sentence selection and ranking, and more.

arXiv:1309.3949

Performance Investigation of Feature Selection Methods

Sentiment analysis or opinion mining has become an open research domain after proliferation of Internet and Web 2.0 social media. People express their attitudes and opinions on social media including blogs, discussion forums, tweets, etc. and, sentiment analysis concerns about detecting and extracting sentiment or opinion from online text. Sentiment based text classification is different from topical text classification since it involves discrimination based on expressed opinion on a topic. Feature selection is significant for sentiment analysis as the opinionated text may have high dimensions, which can adversely affect the performance of sentiment analysis classifier. This paper explores applicability of feature selection methods for sentiment analysis and investigates their performance for classification in term of recall, precision and accuracy. Five feature selection methods (Document Frequency, Information Gain, Gain Ratio, Chi Squared, and Relief-F) and three popular sentiment feature lexicons (HM, GI and Opinion Lexicon) are investigated on movie reviews corpus with a size of 2000 documents. The experimental results show that Information Gain gave consistent results and Gain Ratio performs overall best for sentimental feature selection while sentiment lexicons gave poor performance. Furthermore, we found that performance of the classifier depends on appropriate number of representative feature selected from text.

arXiv:1309.3946

Using Self-Organizing Maps for Sentiment Analysis

Web 2.0 services have enabled people to express their opinions, experience and feelings in the form of user-generated content. Sentiment analysis or opinion mining involves identifying, classifying and aggregating opinions as per their positive or negative polarity. This paper investigates the efficacy of different implementations of Self-Organizing Maps (SOM) for sentiment based visualization and classification of online reviews. Specifically, this paper implements the SOM algorithm for both supervised and unsupervised learning from text documents. The unsupervised SOM algorithm is implemented for sentiment based visualization and classification tasks. For supervised sentiment analysis, a competitive learning algorithm known as Learning Vector Quantization is used. Both algorithms are also compared with their respective multi-pass implementations where a quick rough ordering pass is followed by a fine tuning pass. The experimental results on the online movie review data set show that SOMs are well suited for sentiment based classification and sentiment polarity visualization.

arXiv:1309.3323

Mapping Mutable Genres in Structurally Complex Volumes

To mine large digital libraries in humanistically meaningful ways, scholars need to divide them by genre. This is a task that classification algorithms are well suited to assist, but they need adjustment to address the specific challenges of this domain. Digital libraries pose two problems of scale not usually found in the article datasets used to test these algorithms. 1) Because libraries span several centuries, the genres being identified may change gradually across the time axis. 2) Because volumes are much longer than articles, they tend to be internally heterogeneous, and the classification task needs to begin with segmentation. We describe a multi-layered solution that trains hidden Markov models to segment volumes, and uses ensembles of overlapping classifiers to address historical change. We test this approach on a collection of 469,200 volumes drawn from HathiTrust Digital Library. To demonstrate the humanistic value of these methods, we extract 32,209 volumes of fiction from the digital library, and trace the changing proportions of first- and third-person narration in the corpus. We note that narrative points of view seem to have strong associations with particular themes and genres.

arXiv:1309.3006

The Classification Accuracy of Multiple-Metric Learning Algorithm on Multi-Sensor Fusion

This paper focuses on two main issues; first one is the impact of Similarity Search to learning the training sample in metric space, and searching based on supervised learning classi-fication. In particular, four metrics space searching are based on spatial information that are introduced as the following; Cheby-shev Distance (CD); Bray Curtis Distance (BCD); Manhattan Distance (MD) and Euclidean Distance(ED) classifiers. The second issue investigates the performance of combination of mul-ti-sensor images on the supervised learning classification accura-cy. QuickBird multispectral data (MS) and panchromatic data (PAN) have been used in this study to demonstrate the enhance-ment and accuracy assessment of fused image over the original images. The supervised classification results of fusion image generated better than the MS did. QuickBird and the best results with ED classifier than the other did.

arXiv:1302.4389

Maxout Networks

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.