Search (53 results, page 1 of 3)

0.04650391 = product of:
  0.06975586 = sum of:
    0.008394743 = weight(_text_:a in 1441) [ClassicSimilarity], result of:
      0.008394743 = score(doc=1441,freq=20.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.16114321 = fieldWeight in 1441, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=1441)
    0.06136112 = sum of:
      0.03687593 = weight(_text_:de in 1441) [ClassicSimilarity], result of:
        0.03687593 = score(doc=1441,freq=2.0), product of:
          0.19416152 = queryWeight, product of:
            4.297489 = idf(docFreq=1634, maxDocs=44218)
            0.045180224 = queryNorm
          0.18992399 = fieldWeight in 1441, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            4.297489 = idf(docFreq=1634, maxDocs=44218)
            0.03125 = fieldNorm(doc=1441)
      0.024485188 = weight(_text_:22 in 1441) [ClassicSimilarity], result of:
        0.024485188 = score(doc=1441,freq=2.0), product of:
          0.15821345 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.045180224 = queryNorm
          0.15476047 = fieldWeight in 1441, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.03125 = fieldNorm(doc=1441)
  0.6666667 = coord(2/3)

Abstract

This paper presents a research on syntactic structures known as noun phrases (NP) being applied to increase the effectiveness and efficiency of the mechanisms for the document's classification. Our hypothesis is the fact that the NP can be used instead of single words as a semantic aggregator to reduce the number of words that will be used for the classification system without losing its semantic coverage, increasing its efficiency. The experiment divided the documents classification process in three phases: a) NP preprocessing b) system training; and c) classification experiments. In the first step, a corpus of digitalized texts was submitted to a natural language processing platform1 in which the part-of-speech tagging was done, and them PERL scripts pertaining to the PALAVRAS package were used to extract the Noun Phrases. The preprocessing also involved the tasks of a) removing NP low meaning pre-modifiers, as quantifiers; b) identification of synonyms and corresponding substitution for common hyperonyms; and c) stemming of the relevant words contained in the NP, for similitude checking with other NPs. The first tests with the resulting documents have demonstrated its effectiveness. We have compared the structural similarity of the documents before and after the whole pre-processing steps of phase one. The texts maintained the consistency with the original and have kept the readability. The second phase involves submitting the modified documents to a SVM algorithm to identify clusters and classify the documents. The classification rules are to be established using a machine learning approach. Finally, tests will be conducted to check the effectiveness of the whole process.

Source

Knowledge organization in the 21st century: between historical patterns and future prospects. Proceedings of the Thirteenth International ISKO Conference 19-22 May 2014, Kraków, Poland. Ed.: Wieslaw Babik

Type

a

0.031663023 = product of:
  0.04749453 = sum of:
    0.010618603 = weight(_text_:a in 4913) [ClassicSimilarity], result of:
      0.010618603 = score(doc=4913,freq=8.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.20383182 = fieldWeight in 4913, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0625 = fieldNorm(doc=4913)
    0.03687593 = product of:
      0.07375186 = sum of:
        0.07375186 = weight(_text_:de in 4913) [ClassicSimilarity], result of:
          0.07375186 = score(doc=4913,freq=2.0), product of:
            0.19416152 = queryWeight, product of:
              4.297489 = idf(docFreq=1634, maxDocs=44218)
              0.045180224 = queryNorm
            0.37984797 = fieldWeight in 4913, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.297489 = idf(docFreq=1634, maxDocs=44218)
              0.0625 = fieldNorm(doc=4913)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Source

Knowledge organization for a sustainable world: challenges and perspectives for cultural, scientific, and technological sharing in a connected society : proceedings of the Fourteenth International ISKO Conference 27-29 September 2016, Rio de Janeiro, Brazil / organized by International Society for Knowledge Organization (ISKO), ISKO-Brazil, São Paulo State University ; edited by José Augusto Chaves Guimarães, Suellen Oliveira Milani, Vera Dodebei

Type

a

0.026661396 = product of:
  0.039992094 = sum of:
    0.009385608 = weight(_text_:a in 2759) [ClassicSimilarity], result of:
      0.009385608 = score(doc=2759,freq=4.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.18016359 = fieldWeight in 2759, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.078125 = fieldNorm(doc=2759)
    0.030606484 = product of:
      0.061212968 = sum of:
        0.061212968 = weight(_text_:22 in 2759) [ClassicSimilarity], result of:
          0.061212968 = score(doc=2759,freq=2.0), product of:
            0.15821345 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.045180224 = queryNorm
            0.38690117 = fieldWeight in 2759, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.078125 = fieldNorm(doc=2759)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Date

1. 2.2016 18:25:22

Type

a

0.015016008 = product of:
  0.022524012 = sum of:
    0.010281418 = weight(_text_:a in 1442) [ClassicSimilarity], result of:
      0.010281418 = score(doc=1442,freq=30.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.19735932 = fieldWeight in 1442, product of:
          5.477226 = tf(freq=30.0), with freq of:
            30.0 = termFreq=30.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=1442)
    0.012242594 = product of:
      0.024485188 = sum of:
        0.024485188 = weight(_text_:22 in 1442) [ClassicSimilarity], result of:
          0.024485188 = score(doc=1442,freq=2.0), product of:
            0.15821345 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.045180224 = queryNorm
            0.15476047 = fieldWeight in 1442, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03125 = fieldNorm(doc=1442)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

The main objective of this research was to analyze whether there was a characteristic distribution behavior of relevant terms over a scientific text that could contribute as a criterion for their process of automatic indexing. The terms considered in this study were only full noun phrases contained in the texts themselves. The texts were considered a total of 98 doctoral theses of the eight areas of knowledge in a same university. Initially, 20 full noun phrases were automatically extracted from each text as candidates to be the most relevant terms, and each author of each text assigned a relevance value 0-6 (not relevant and highly relevant, respectively) for each of the 20 noun phrases sent. Only, 22.1 % of noun phrases were considered not relevant. A relevance values of the terms assigned by the authors were associated with their positions in the text. Each full noun phrases found in the text was considered as a valid linear position. The results that were obtained showed values resulting from this distribution by considering two types of position: linear, with values consolidated into ten equal consecutive parts; and structural, considering parts of the text (such as introduction, development and conclusion). As a result of considerable importance, all areas of knowledge related to the Natural Sciences showed a characteristic behavior in the distribution of relevant terms, as well as all areas of knowledge related to Social Sciences showed the same characteristic behavior of distribution, but distinct from the Natural Sciences. The difference of the distribution behavior between the Natural and Social Sciences can be clearly visualized through graphs. All behaviors, including the general behavior of all areas of knowledge together, were characterized in polynomial equations and can be applied in future as criteria for automatic indexing. Until the present date this work has become inedited of for two reasons: to present a method for characterizing the distribution of relevant terms in a scientific text, and also, through this method, pointing out a quantitative trait difference between the Natural and Social Sciences.

Source

Knowledge organization in the 21st century: between historical patterns and future prospects. Proceedings of the Thirteenth International ISKO Conference 19-22 May 2014, Kraków, Poland. Ed.: Wieslaw Babik

Type

a

0.01211905 = product of:
  0.018178575 = sum of:
    0.00593598 = weight(_text_:a in 5499) [ClassicSimilarity], result of:
      0.00593598 = score(doc=5499,freq=10.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11394546 = fieldWeight in 5499, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=5499)
    0.012242594 = product of:
      0.024485188 = sum of:
        0.024485188 = weight(_text_:22 in 5499) [ClassicSimilarity], result of:
          0.024485188 = score(doc=5499,freq=2.0), product of:
            0.15821345 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.045180224 = queryNorm
            0.15476047 = fieldWeight in 5499, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03125 = fieldNorm(doc=5499)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

Purpose Modern mathematicians and scientists of math-related disciplines often use Document Preparation Systems (DPS) to write and Computer Algebra Systems (CAS) to calculate mathematical expressions. Usually, they translate the expressions manually between DPS and CAS. This process is time-consuming and error-prone. The purpose of this paper is to automate this translation. This paper uses Maple and Mathematica as the CAS, and LaTeX as the DPS. Design/methodology/approach Bruce Miller at the National Institute of Standards and Technology (NIST) developed a collection of special LaTeX macros that create links from mathematical symbols to their definitions in the NIST Digital Library of Mathematical Functions (DLMF). The authors are using these macros to perform rule-based translations between the formulae in the DLMF and CAS. Moreover, the authors develop software to ease the creation of new rules and to discover inconsistencies. Findings The authors created 396 mappings and translated 58.8 percent of DLMF formulae (2,405 expressions) successfully between Maple and DLMF. For a significant percentage, the special function definitions in Maple and the DLMF were different. An atomic symbol in one system maps to a composite expression in the other system. The translator was also successfully used for automatic verification of mathematical online compendia and CAS. The evaluation techniques discovered two errors in the DLMF and one defect in Maple. Originality/value This paper introduces the first translation tool for special functions between LaTeX and CAS. The approach improves error-prone manual translations and can be used to verify mathematical online compendia and CAS.

Date

20. 1.2015 18:30:22

Type

a

0.0061459886 = product of:
  0.018437965 = sum of:
    0.018437965 = product of:
      0.03687593 = sum of:
        0.03687593 = weight(_text_:de in 3081) [ClassicSimilarity], result of:
          0.03687593 = score(doc=3081,freq=2.0), product of:
            0.19416152 = queryWeight, product of:
              4.297489 = idf(docFreq=1634, maxDocs=44218)
              0.045180224 = queryNorm
            0.18992399 = fieldWeight in 3081, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.297489 = idf(docFreq=1634, maxDocs=44218)
              0.03125 = fieldNorm(doc=3081)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Content

Vgl.: https://www.ibi.hu-berlin.de/de/archiv/forschung/prom_habil/dissertationen/Tavakolizadeh-Ravari2007. Vgl. auch: http://mravari.blogfa.com/post-20.aspxgl.

0.0043799505 = product of:
  0.013139851 = sum of:
    0.013139851 = weight(_text_:a in 2091) [ClassicSimilarity], result of:
      0.013139851 = score(doc=2091,freq=16.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.25222903 = fieldWeight in 2091, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=2091)
  0.33333334 = coord(1/3)

Abstract

During the BMWI granted project "Print-IT", the need of a thesaurus based uniform and consistent language for the German printing industry became evident. In this paper we introduce a semi-automatic construction approach for such a thesaurus and present a workflow which supports users to generate thesaurus typical information structures from relevant digitalized resources with the help of common IT-tools.

Type

a

0.0039480343 = product of:
  0.011844102 = sum of:
    0.011844102 = weight(_text_:a in 1874) [ClassicSimilarity], result of:
      0.011844102 = score(doc=1874,freq=52.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.22735618 = fieldWeight in 1874, product of:
          7.2111025 = tf(freq=52.0), with freq of:
            52.0 = termFreq=52.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.02734375 = fieldNorm(doc=1874)
  0.33333334 = coord(1/3)

Content

"People can summarize a complex scene in a few words without thinking twice. It's much more difficult for computers. But we've just gotten a bit closer -- we've developed a machine-learning system that can automatically produce captions (like the three above) to accurately describe images the first time it sees them. This kind of system could eventually help visually impaired people understand pictures, provide alternate text for images in parts of the world where mobile connections are slow, and make it easier for everyone to search on Google for images. Recent research has greatly improved object detection, classification, and labeling. But accurately describing a complex scene requires a deeper representation of what's going on in the scene, capturing how the various objects relate to one another and translating it all into natural-sounding language. Many efforts to construct computer-generated natural descriptions of images propose combining current state-of-the-art techniques in both computer vision and natural language processing to form a complete image description approach. But what if we instead merged recent computer vision and language models into a single jointly trained system, taking an image and directly producing a human readable sequence of words to describe it? This idea comes from recent advances in machine translation between languages, where a Recurrent Neural Network (RNN) transforms, say, a French sentence into a vector representation, and a second RNN uses that vector representation to generate a target sentence in German. Now, what if we replaced that first RNN and its input words with a deep Convolutional Neural Network (CNN) trained to classify objects in images? Normally, the CNN's last layer is used in a final Softmax among known classes of objects, assigning a probability that each object might be in the image. But if we remove that final layer, we can instead feed the CNN's rich encoding of the image into a RNN designed to produce phrases. We can then train the whole system directly on images and their captions, so it maximizes the likelihood that descriptions it produces best match the training descriptions for each image.
Our experiments with this system on several openly published datasets, including Pascal, Flickr8k, Flickr30k and SBU, show how robust the qualitative results are -- the generated sentences are quite reasonable. It also performs well in quantitative evaluations with the Bilingual Evaluation Understudy (BLEU), a metric used in machine translation to evaluate the quality of generated sentences. A picture may be worth a thousand words, but sometimes it's the words that are most useful -- so it's important we figure out ways to translate from images to words automatically and accurately. As the datasets suited to learning image descriptions grow and mature, so will the performance of end-to-end approaches like this. We look forward to continuing developments in systems that can read images and generate good natural-language descriptions. To get more details about the framework used to generate descriptions from images, as well as the model evaluation, read the full paper here." Vgl. auch: https://news.ycombinator.com/item?id=8621658.

Source

http://googleresearch.blogspot.de/2014/11/a-picture-is-worth-thousand-coherent.html

0.003793148 = product of:
  0.011379444 = sum of:
    0.011379444 = weight(_text_:a in 5236) [ClassicSimilarity], result of:
      0.011379444 = score(doc=5236,freq=12.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.21843673 = fieldWeight in 5236, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5236)
  0.33333334 = coord(1/3)

Abstract

The Black Book Interactive Project at the University of Kansas (KU) is developing an expanded corpus of novels by African American authors, with an emphasis on lesser known writers and a goal of expanding research in this field. Using a custom metadata schema with an emphasis on race-related elements, each novel is analyzed for a variety of elements such as literary style, targeted content analysis, historical context, and other areas. Librarians at KU have worked to develop a variety of computational text analysis processes designed to assist with specific aspects of this metadata collection, including text mining and natural language processing, automated subject extraction based on word sense disambiguation, harvesting data from Wikidata, and other actions.

Type

a

0.003754243 = product of:
  0.011262729 = sum of:
    0.011262729 = weight(_text_:a in 1868) [ClassicSimilarity], result of:
      0.011262729 = score(doc=1868,freq=16.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.2161963 = fieldWeight in 1868, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=1868)
  0.33333334 = coord(1/3)

Abstract

We present a model that generates free-form natural language descriptions of image regions. Our model leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between text and visual data. Our approach is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate the effectiveness of our alignment model with ranking experiments on Flickr8K, Flickr30K and COCO datasets, where we substantially improve on the state of the art. We then show that the sentences created by our generative model outperform retrieval baselines on the three aforementioned datasets and a new dataset of region-level annotations.

Type

a

0.0035117732 = product of:
  0.010535319 = sum of:
    0.010535319 = weight(_text_:a in 3320) [ClassicSimilarity], result of:
      0.010535319 = score(doc=3320,freq=14.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.20223314 = fieldWeight in 3320, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=3320)
  0.33333334 = coord(1/3)

Abstract

The goal of this research is to develop a generic ontological model for proverbs that unifies potential classification criteria and various characteristics of proverbs to enable their effective retrieval and large-scale analysis. Because proverbs can be described and indexed by multiple characteristics and criteria, we built a multidimensional ontology suitable for proverb classification. To evaluate the effectiveness of the constructed ontology for improving search and retrieval of proverbs, a large-scale user experiment was arranged with 70 users who were asked to search a proverb repository using ontology-based and free-text search interfaces. The comparative analysis of the results shows that the use of this ontology helped to substantially improve the search recall, precision, user satisfaction, and efficiency and to minimize user effort during the search process. A practical contribution of this work is an automated web-based proverb search and retrieval system which incorporates the proposed ontological scheme and an initial corpus of ontology-based annotated proverbs.

Type

a

0.003462655 = product of:
  0.010387965 = sum of:
    0.010387965 = weight(_text_:a in 2933) [ClassicSimilarity], result of:
      0.010387965 = score(doc=2933,freq=10.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.19940455 = fieldWeight in 2933, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=2933)
  0.33333334 = coord(1/3)

Abstract

We propose a method for improving access to scientific literature by analyzing the content of research papers beyond citation links and topic tracking. Our model relies on a typology of explicit semantic relations. These relations are instantiated in the abstract/introduction part of the papers and can be identified automatically using textual data and external ontologies. Preliminary results show a promising precision in unsupervised relationship classification.

Type

a

0.00325127 = product of:
  0.009753809 = sum of:
    0.009753809 = weight(_text_:a in 1557) [ClassicSimilarity], result of:
      0.009753809 = score(doc=1557,freq=12.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.18723148 = fieldWeight in 1557, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=1557)
  0.33333334 = coord(1/3)

Abstract

In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on three benchmark datasets (IAPR TC-12 [8], Flickr 8K [28], and Flickr 30K [13]). Our model outperforms the state-of-the-art generative method. In addition, the m-RNN model can be applied to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.

Type

a

0.00325127 = product of:
  0.009753809 = sum of:
    0.009753809 = weight(_text_:a in 1871) [ClassicSimilarity], result of:
      0.009753809 = score(doc=1871,freq=12.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.18723148 = fieldWeight in 1871, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=1871)
  0.33333334 = coord(1/3)

Abstract

Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images and sentences while the decoder can generate novel descriptions from scratch. Using LSTM to encode sentences, we match the state-of-the-art performance on Flickr8K and Flickr30K without using object detections. We also set new best results when using the 19-layer Oxford convolutional network. Furthermore we show that with linear encoders, the learned embedding space captures multimodal regularities in terms of vector space arithmetic e.g. *image of a blue car* - "blue" + "red" is near images of red cars. Sample captions generated for 800 images are made available for comparison.

Type

a

0.003128536 = product of:
  0.009385608 = sum of:
    0.009385608 = weight(_text_:a in 2161) [ClassicSimilarity], result of:
      0.009385608 = score(doc=2161,freq=16.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.18016359 = fieldWeight in 2161, product of:
          4.0 = tf(freq=16.0), with freq of:
            16.0 = termFreq=16.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2161)
  0.33333334 = coord(1/3)

Abstract

Millions of micro texts are published every day on Twitter. Identifying the sentiment present in them can be helpful for measuring the frame of mind of the public, their satisfaction with respect to a product, or their support of a social event. In this context, polarity classification is a subfield of sentiment analysis focused on determining whether the content of a text is objective or subjective, and in the latter case, if it conveys a positive or a negative opinion. Most polarity detection techniques tend to take into account individual terms in the text and even some degree of linguistic knowledge, but they do not usually consider syntactic relations between words. This article explores how relating lexical, syntactic, and psychometric information can be helpful to perform polarity classification on Spanish tweets. We provide an evaluation for both shallow and deep linguistic perspectives. Empirical results show an improved performance of syntactic approaches over pure lexical models when using large training sets to create a classifier, but this tendency is reversed when small training collections are used.

Type

a

0.0030970925 = product of:
  0.009291277 = sum of:
    0.009291277 = weight(_text_:a in 2930) [ClassicSimilarity], result of:
      0.009291277 = score(doc=2930,freq=8.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.17835285 = fieldWeight in 2930, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=2930)
  0.33333334 = coord(1/3)

Abstract

We present a framework for keyphrase extraction from scientific journals in diverse research fields. While journal articles are often provided with manually assigned keywords, it is not clear how to automatically extract keywords and measure their significance for a set of journal articles. We compare extracted keyphrases from journals in the fields of astrophysics, mathematics, physics, and computer science. We show that the presented statistics-based framework is able to demonstrate differences among journals, and that the extracted keyphrases can be used to represent journal or conference research topics, dynamics, and specificity.

Type

a

0.00296799 = product of:
  0.00890397 = sum of:
    0.00890397 = weight(_text_:a in 2721) [ClassicSimilarity], result of:
      0.00890397 = score(doc=2721,freq=10.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.1709182 = fieldWeight in 2721, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=2721)
  0.33333334 = coord(1/3)

Abstract

In this paper, we describe a user-centered design of an automated multifaceted concept-based indexing framework which analyzes the semantics of the Web image contextual information and classifies it into five broad semantic concept facets: signal, object, abstract, scene, and relational; and identifies the semantic relationships between the concepts. An important aspect of our indexing model is that it relates to the users' levels of image descriptions. Also, a major contribution relies on the fact that the classification is performed automatically with the raw image contextual information extracted from any general webpage and is not solely based on image tags like state-of-the-art solutions. Human Language Technology techniques and an external knowledge base are used to analyze the information both syntactically and semantically. Experimental results on a human-annotated Web image collection and corresponding contextual information indicate that our method outperforms empirical frameworks employing tf-idf and location-based tf-idf weighting schemes as well as n-gram indexing in a recall/precision based evaluation framework.

Type

a

0.0029264777 = product of:
  0.008779433 = sum of:
    0.008779433 = weight(_text_:a in 1869) [ClassicSimilarity], result of:
      0.008779433 = score(doc=1869,freq=14.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.1685276 = fieldWeight in 1869, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1869)
  0.33333334 = coord(1/3)

Abstract

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions. Our model is often quite accurate, which we verify both qualitatively and quantitatively. For instance, while the current state-of-the-art BLEU-1 score (the higher the better) on the Pascal dataset is 25, our approach yields 59, to be compared to human performance around 69. We also show BLEU-1 score improvements on Flickr30k, from 56 to 66, and on SBU, from 19 to 28. Lastly, on the newly released COCO dataset, we achieve a BLEU-4 of 27.7, which is the current state-of-the-art.

Content

Vgl.: http://googleresearch.blogspot.de/2014/11/a-picture-is-worth-thousand-coherent.html. Vgl. auch: https://news.ycombinator.com/item?id=8621658.

0.0029264777 = product of:
  0.008779433 = sum of:
    0.008779433 = weight(_text_:a in 3151) [ClassicSimilarity], result of:
      0.008779433 = score(doc=3151,freq=14.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.1685276 = fieldWeight in 3151, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3151)
  0.33333334 = coord(1/3)

Abstract

Arabic news articles in electronic collections are difficult to study. Browsing by category is rarely supported. Although helpful machine-learning methods have been applied successfully to similar situations for English news articles, limited research has been completed to yield suitable solutions for Arabic news. In connection with a Qatar National Research Fund (QNRF)-funded project to build digital library community and infrastructure in Qatar, we developed software for browsing a collection of about 237,000 Arabic news articles, which should be applicable to other Arabic news collections. We designed a simple taxonomy for Arabic news stories that is suitable for the needs of Qatar and other nations, is compatible with the subject codes of the International Press Telecommunications Council, and was enhanced with the aid of a librarian expert as well as five Arabic-speaking volunteers. We developed tailored stemming (i.e., a new Arabic light stemmer called P-Stemmer) and automatic classification methods (the best being binary Support Vector Machines classifiers) to work with the taxonomy. Using evaluation techniques commonly used in the information retrieval community, including 10-fold cross-validation and the Wilcoxon signed-rank test, we showed that our approach to stemming and classification is superior to state-of-the-art techniques.

Type

a

0.0029264777 = product of:
  0.008779433 = sum of:
    0.008779433 = weight(_text_:a in 3311) [ClassicSimilarity], result of:
      0.008779433 = score(doc=3311,freq=14.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.1685276 = fieldWeight in 3311, product of:
          3.7416575 = tf(freq=14.0), with freq of:
            14.0 = termFreq=14.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3311)
  0.33333334 = coord(1/3)

Abstract

Tools for automatic subject assignment help deal with scale and sustainability in creating and enriching metadata, establishing more connections across and between resources and enhancing consistency. Although some software vendors and experimental researchers claim the tools can replace manual subject indexing, hard scientific evidence of their performance in operating information environments is scarce. A major reason for this is that research is usually conducted in laboratory conditions, excluding the complexities of real-life systems and situations. The article reviews and discusses issues with existing evaluation approaches such as problems of aboutness and relevance assessments, implying the need to use more than a single "gold standard" method when evaluating indexing and retrieval, and proposes a comprehensive evaluation framework. The framework is informed by a systematic review of the literature on evaluation approaches: evaluating indexing quality directly through assessment by an evaluator or through comparison with a gold standard, evaluating the quality of computer-assisted indexing directly in the context of an indexing workflow, and evaluating indexing quality indirectly through analyzing retrieval performance.

Type

a