PyTorchKR Papers

최신 논문

총 1,314편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1807.00099

Generating Titles for Web Tables

Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their dependence on suitable titles existing a priori. In our user study, we observe that the relevant information for the title tends to be scattered across the page, and often--more than 80% of the time--does not appear verbatim anywhere in the page. We propose instead the application of a sequence-to-sequence neural network model as a more generalizable means of generating high-quality titles. This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title. We validate this approach with human evaluation on sample web tables and report that while sequence models with only a copy mechanism or only a generation mechanism are easily outperformed by simple selection-based baselines, the model with both capabilities outperforms them all, approaching the quality of crowdsourced titles while training on fewer than ten thousand examples. To the best of our knowledge, the proposed technique is the first to consider text generation methods for table titles and establishes a new state of the art.

arXiv:1806.07745

Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing

In the United States, the Federal Communications Commission has adopted rules permitting commercial wireless networks to share spectrum with federal incumbents in the 3.5~GHz Citizens Broadband Radio Service band. These rules require commercial systems to vacate the band when sensors detect radars operated by the U.S. military; a key example being the SPN-43 air traffic control radar. Such sensors require highly-accurate detection algorithms to meet their operating requirements. In this paper, using a library of over 14,000 3.5~GHz band spectrograms collected by a recent measurement campaign, we investigate the performance of thirteen methods for SPN-43 radar detection. Namely, we compare classical methods from signal detection theory and machine learning to several deep learning architectures. We demonstrate that machine learning algorithms appreciably outperform classical signal detection methods. Specifically, we find that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity. Last, we apply this three-layer network to generate descriptive statistics for the full 3.5~GHz spectrogram library. Our findings highlight potential weaknesses of classical methods and strengths of modern machine learning algorithms for radar detection in the 3.5~GHz band.

arXiv:1304.3082

Reasoning With Uncertain Knowledge

A model of knowledge representation is described in which propositional facts and the relationships among them can be supported by other facts. The set of knowledge which can be supported is called the set of cognitive units, each having associated descriptions of their explicit and implicit support structures, summarizing belief and reliability of belief. This summary is precise enough to be useful in a computational model while remaining descriptive of the underlying symbolic support structure. When a fact supports another supportive relationship between facts we call this meta-support. This facilitates reasoning about both the propositional knowledge. and the support structures underlying it.

arXiv:1212.1362

Stochastic model for the vocabulary growth in natural languages

We propose a stochastic model for the number of different words in a given database which incorporates the dependence on the database size and historical changes. The main feature of our model is the existence of two different classes of words: (i) a finite number of core-words which have higher frequency and do not affect the probability of a new word to be used; and (ii) the remaining virtually infinite number of noncore-words which have lower frequency and once used reduce the probability of a new word to be used in the future. Our model relies on a careful analysis of the google-ngram database of books published in the last centuries and its main consequence is the generalization of Zipf's and Heaps' law to two scaling regimes. We confirm that these generalizations yield the best simple description of the data among generic descriptive models and that the two free parameters depend only on the language but not on the database. From the point of view of our model the main change on historical time scales is the composition of the specific words included in the finite list of core-words, which we observe to decay exponentially in time with a rate of approximately 30 words per year for English.

arXiv:1210.1207

Learning Human Activities and Object Affordances from RGB-D Videos

Understanding human activities and object affordances are two very important skills, especially for personal robots which operate in human environments. In this work, we consider the problem of extracting a descriptive labeling of the sequence of sub-activities being performed by a human, and more importantly, of their interactions with the objects in the form of associated affordances. Given a RGB-D video, we jointly model the human activities and object affordances as a Markov random field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural support vector machine (SSVM) approach, where labelings over various alternate temporal segmentations are considered as latent variables. We tested our method on a challenging dataset comprising 120 activity videos collected from 4 subjects, and obtained an accuracy of 79.4% for affordance, 63.4% for sub-activity and 75.0% for high-level activity labeling. We then demonstrate the use of such descriptive labeling in performing assistive tasks by a PR2 robot.

arXiv:1310.0316

Classifying Traffic Scenes Using The GIST Image Descriptor

This paper investigates classification of traffic scenes in a very low bandwidth scenario, where an image should be coded by a small number of features. We introduce a novel dataset, called the FM1 dataset, consisting of 5615 images of eight different traffic scenes: open highway, open road, settlement, tunnel, tunnel exit, toll booth, heavy traffic and the overpass. We evaluate the suitability of the GIST descriptor as a representation of these images, first by exploring the descriptor space using PCA and k-means clustering, and then by using an SVM classifier and recording its 10-fold cross-validation performance on the introduced FM1 dataset. The obtained recognition rates are very encouraging, indicating that the use of the GIST descriptor alone could be sufficiently descriptive even when very high performance is required.

arXiv:1312.3388

Online Bayesian Passive-Aggressive Learning

Online Passive-Aggressive (PA) learning is an effective framework for performing max-margin online learning. But the deterministic formulation and estimated single large-margin model could limit its capability in discovering descriptive structures underlying complex data. This pa- per presents online Bayesian Passive-Aggressive (BayesPA) learning, which subsumes the online PA and extends naturally to incorporate latent variables and perform nonparametric Bayesian inference, thus providing great flexibility for explorative analysis. We apply BayesPA to topic modeling and derive efficient online learning algorithms for max-margin topic models. We further develop nonparametric methods to resolve the number of topics. Experimental results on real datasets show that our approaches significantly improve time efficiency while maintaining comparable results with the batch counterparts.

arXiv:1307.0845

The SP theory of intelligence: benefits and applications

This article describes existing and expected benefits of the "SP theory of intelligence", and some potential applications. The theory aims to simplify and integrate ideas across artificial intelligence, mainstream computing, and human perception and cognition, with information compression as a unifying theme. It combines conceptual simplicity with descriptive and explanatory power across several areas of computing and cognition. In the "SP machine" -- an expression of the SP theory which is currently realized in the form of a computer model -- there is potential for an overall simplification of computing systems, including software. The SP theory promises deeper insights and better solutions in several areas of application including, most notably, unsupervised learning, natural language processing, autonomous robots, computer vision, intelligent databases, software engineering, information compression, medical diagnosis and big data. There is also potential in areas such as the semantic web, bioinformatics, structuring of documents, the detection of computer viruses, data fusion, new kinds of computer, and the development of scientific theories. The theory promises seamless integration of structures and functions within and between different areas of application. The potential value, worldwide, of these benefits and applications is at least $190 billion each year. Further development would be facilitated by the creation of a high-parallel, open-source version of the SP machine, available to researchers everywhere.

arXiv:1401.0871

Stylistic Clusters and the Syrian/South Syrian Tradition of First-Millennium BCE Levantine Ivory Carving: A Machine Learning Approach

Thousands of first-millennium BCE ivory carvings have been excavated from Neo-Assyrian sites in Mesopotamia (primarily Nimrud, Khorsabad, and Arslan Tash) hundreds of miles from their Levantine production contexts. At present, their specific manufacture dates and workshop localities are unknown. Relying on subjective, visual methods, scholars have grappled with their classification and regional attribution for over a century. This study combines visual approaches with machine-learning techniques to offer data-driven perspectives on the classification and attribution of this early Iron Age corpus. The study sample consisted of 162 sculptures of female figures. We have developed an algorithm that clusters the ivories based on a combination of descriptive and anthropometric data. The resulting categories, which are based on purely statistical criteria, show good agreement with conventional art historical classifications, while revealing new perspectives, especially with regard to the contested Syrian/South Syrian/Intermediate tradition. Specifically, we have identified that objects of the Syrian/South Syrian/Intermediate tradition may be more closely related to Phoenician objects than to North Syrian objects; we offer a reconsideration of a subset of Phoenician objects, and we confirm Syrian/South Syrian/Intermediate stylistic subgroups that might distinguish networks of acquisition among the sites of Nimrud, Khorsabad, Arslan Tash and the Levant. We have also identified which features are most significant in our cluster assignments and might thereby be most diagnostic of regional carving traditions. In short, our study both corroborates traditional visual classification methods and demonstrates how machine-learning techniques may be employed to reveal complementary information not accessible through the exclusively visual analysis of an archaeological corpus.

arXiv:1405.7711

Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language

We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system that learns to sportscast simulated robot soccer games in both English and Korean without any language-specific prior knowledge. Training employs only ambiguous supervision consisting of a stream of descriptive textual comments and a sequence of events extracted from the simulation trace. The system simultaneously establishes correspondences between individual comments and the events that they describe while building a translation model that supports both parsing and generation. We also present a novel algorithm for learning which events are worth describing. Human evaluations of the generated commentaries indicate they are of reasonable quality and in some cases even on par with those produced by humans for our limited domain.

arXiv:1401.4603

Semantic Similarity Measures Applied to an Ontology for Human-Like Interaction

The focus of this paper is the calculation of similarity between two concepts from an ontology for a Human-Like Interaction system. In order to facilitate this calculation, a similarity function is proposed based on five dimensions (sort, compositional, essential, restrictive and descriptive) constituting the structure of ontological knowledge. The paper includes a proposal for computing a similarity function for each dimension of knowledge. Later on, the similarity values obtained are weighted and aggregated to obtain a global similarity measure. In order to calculate those weights associated to each dimension, four training methods have been proposed. The training methods differ in the element to fit: the user, concepts or pairs of concepts, and a hybrid approach. For evaluating the proposal, the knowledge base was fed from WordNet and extended by using a knowledge editing toolkit (Cognos). The evaluation of the proposal is carried out through the comparison of system responses with those given by human test subjects, both providing a measure of the soundness of the procedure and revealing ways in which the proposal may be improved.

arXiv:1403.3668

Language Heedless of Logic - Philosophy Mindful of What? Failures of Distributive and Absorption Laws

Much of philosophical logic and all of philosophy of language make empirical claims about the vernacular natural language. They presume semantics under which `and' and `or' are related by the dually paired distributive and absorption laws. However, at least one of each pair of laws fails in the vernacular. `Implicature'-based auxiliary theories associated with the programme of H.P. Grice do not prove remedial. Conceivable alternatives that might replace the familiar logics as descriptive instruments are briefly noted: (i) substructural logics and (ii) meaning composition in linear algebras over the reals, occasionally constrained by norms of classical logic. Alternative (ii) locates the problem in violations of one of the idempotent laws. Reasons for a lack of curiosity about elementary and easily testable implications of the received theory are considered. The concept of `reflective equilibrium' is critically examined for its role in reconciling normative desiderata and descriptive commitments.

arXiv:1404.3610

Targeting HIV-related Medication Side Effects and Sentiment Using Twitter Data

We present a descriptive analysis of Twitter data. Our study focuses on extracting the main side effects associated with HIV treatments. The crux of our work was the identification of personal tweets referring to HIV. We summarize our results in an infographic aimed at the general public. In addition, we present a measure of user sentiment based on hand-rated tweets.

arXiv:1401.4112

A bi-level view of inpainting - based image compression

Inpainting based image compression approaches, especially linear and non-linear diffusion models, are an active research topic for lossy image compression. The major challenge in these compression models is to find a small set of descriptive supporting points, which allow for an accurate reconstruction of the original image. It turns out in practice that this is a challenging problem even for the simplest Laplacian interpolation model. In this paper, we revisit the Laplacian interpolation compression model and introduce two fast algorithms, namely successive preconditioning primal dual algorithm and the recently proposed iPiano algorithm, to solve this problem efficiently. Furthermore, we extend the Laplacian interpolation based compression model to a more general form, which is based on principles from bi-level optimization. We investigate two different variants of the Laplacian model, namely biharmonic interpolation and smoothed Total Variation regularization. Our numerical results show that significant improvements can be obtained from the biharmonic interpolation model, and it can recover an image with very high quality from only 5% pixels.

arXiv:1405.3727

Student Dropout Risk Assessment in Undergraduate Course at Residential University

Student dropout prediction is an indispensable for numerous intelligent systems to measure the education system and success rate of any university as well as throughout the university in the world. Therefore, it becomes essential to develop efficient methods for prediction of the students at risk of dropping out, enabling the adoption of proactive process to minimize the situation. Thus, this research work propose a prototype machine learning tool which can automatically recognize whether the student will continue their study or drop their study using classification technique based on decision tree and extract hidden information from large data about what factors are responsible for dropout student. Further the contribution of factors responsible for dropout risk was studied using discriminant analysis and to extract interesting correlations, frequent patterns, associations or casual structures among significant datasets, Association rule mining was applied. In this study, the descriptive statistics analysis was carried out to measure the quality of data using SPSS 20.0 statistical software and application of decision tree and association rule were carried out by using WEKA data mining tool.

arXiv:1405.6678

Hybrid Type-Logical Grammars, First-Order Linear Logic and the Descriptive Inadequacy of Lambda Grammars

In this article we show that hybrid type-logical grammars are a fragment of first-order linear logic. This embedding result has several important consequences: it not only provides a simple new proof theory for the calculus, thereby clarifying the proof-theoretic foundations of hybrid type-logical grammars, but, since the translation is simple and direct, it also provides several new parsing strategies for hybrid type-logical grammars. Second, NP-completeness of hybrid type-logical grammars follows immediately. The main embedding result also sheds new light on problems with lambda grammars/abstract categorial grammars and shows lambda grammars/abstract categorial grammars suffer from problems of over-generation and from problems at the syntax-semantics interface unlike any other categorial grammar.

arXiv:1408.1487

Robust Feature Selection by Mutual Information Distributions

Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must consider sample-to-population inferential approaches. This paper deals with the distribution of mutual information, as obtained in a Bayesian framework by a second-order Dirichlet prior distribution. The exact analytical expression for the mean and an analytical approximation of the variance are reported. Asymptotic approximations of the distribution are proposed. The results are applied to the problem of selecting features for incremental learning and classification of the naive Bayes classifier. A fast, newly defined method is shown to outperform the traditional approach based on empirical mutual information on a number of real data sets. Finally, a theoretical development is reported that allows one to efficiently extend the above methods to incomplete samples in an easy and effective way.

arXiv:1411.1784

Conditional Generative Adversarial Nets

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digits conditioned on class labels. We also illustrate how this model could be used to learn a multi-modal model, and provide preliminary examples of an application to image tagging in which we demonstrate how this approach can generate descriptive tags which are not part of training labels.

arXiv:1410.5224

Supervised mid-level features for word image representation

This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be supplied with these representations to produce models useful for word retrieval or recognition tasks. Although many works have focused on the machine learning aspect once a global representation has been produced, little work has been devoted to the construction of those base image representations: most works use standard coding and aggregation techniques directly on top of standard computer vision features such as SIFT or HOG. We propose to learn local mid-level features suitable for building word image representations. These features are learnt by leveraging character bounding box annotations on a small set of training images. However, contrary to other approaches that use character bounding box information, our approach does not rely on detecting the individual characters explicitly at testing time. Our local mid-level features can then be aggregated to produce a global word image signature. When pairing these features with the recent word attributes framework of Almaz\'an et al., we obtain results comparable with or better than the state-of-the-art on matching and recognition tasks using global descriptors of only 96 dimensions.

arXiv:1409.5623

Interactive Visual Exploration of Topic Models using Graphs

Probabilistic topic modeling is a popular and powerful family of tools for uncovering thematic structure in large sets of unstructured text documents. While much attention has been directed towards the modeling algorithms and their various extensions, comparatively few studies have concerned how to present or visualize topic models in meaningful ways. In this paper, we present a novel design that uses graphs to visually communicate topic structure and meaning. By connecting topic nodes via descriptive keyterms, the graph representation reveals topic similarities, topic meaning and shared, ambiguous keyterms. At the same time, the graph can be used for information retrieval purposes, to find documents by topic or topic subsets. To exemplify the utility of the design, we illustrate its use for organizing and exploring corpora of financial patents.