Search (9 results, page 1 of 1)

  • × theme_ss:"Automatisches Indexieren"
  • × type_ss:"el"
  • × year_i:[2010 TO 2020}
  1. Gábor, K.; Zargayouna, H.; Tellier, I.; Buscaldi, D.; Charnois, T.: ¬A typology of semantic relations dedicated to scientific literature analysis (2016) 0.08
    0.083605506 = product of:
      0.1393425 = sum of:
        0.032756116 = weight(_text_:retrieval in 2933) [ClassicSimilarity], result of:
          0.032756116 = score(doc=2933,freq=2.0), product of:
            0.14001551 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.04628742 = queryNorm
            0.23394634 = fieldWeight in 2933, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2933)
        0.08752273 = weight(_text_:semantic in 2933) [ClassicSimilarity], result of:
          0.08752273 = score(doc=2933,freq=4.0), product of:
            0.19245663 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.04628742 = queryNorm
            0.45476598 = fieldWeight in 2933, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2933)
        0.019063652 = product of:
          0.038127303 = sum of:
            0.038127303 = weight(_text_:web in 2933) [ClassicSimilarity], result of:
              0.038127303 = score(doc=2933,freq=2.0), product of:
                0.15105948 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.04628742 = queryNorm
                0.25239927 = fieldWeight in 2933, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=2933)
          0.5 = coord(1/2)
      0.6 = coord(3/5)
    
    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.
    Content
    Vortrag, "Semantics, Analytics, Visualisation: Enhancing Scholarly Data Workshop co-located with the 25th International World Wide Web Conference April 11, 2016 - Montreal, Canada", Montreal 2016.
    Theme
    Semantisches Umfeld in Indexierung u. Retrieval
  2. Karpathy, A.; Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions (2015) 0.03
    0.032449383 = product of:
      0.08112346 = sum of:
        0.028076671 = weight(_text_:retrieval in 1868) [ClassicSimilarity], result of:
          0.028076671 = score(doc=1868,freq=2.0), product of:
            0.14001551 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.04628742 = queryNorm
            0.20052543 = fieldWeight in 1868, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.046875 = fieldNorm(doc=1868)
        0.05304678 = weight(_text_:semantic in 1868) [ClassicSimilarity], result of:
          0.05304678 = score(doc=1868,freq=2.0), product of:
            0.19245663 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.04628742 = queryNorm
            0.2756298 = fieldWeight in 1868, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.046875 = fieldNorm(doc=1868)
      0.4 = coord(2/5)
    
    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.
  3. Junger, U.: Can indexing be automated? : the example of the Deutsche Nationalbibliothek (2012) 0.03
    0.032380622 = product of:
      0.08095156 = sum of:
        0.06188791 = weight(_text_:semantic in 1717) [ClassicSimilarity], result of:
          0.06188791 = score(doc=1717,freq=2.0), product of:
            0.19245663 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.04628742 = queryNorm
            0.32156807 = fieldWeight in 1717, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1717)
        0.019063652 = product of:
          0.038127303 = sum of:
            0.038127303 = weight(_text_:web in 1717) [ClassicSimilarity], result of:
              0.038127303 = score(doc=1717,freq=2.0), product of:
                0.15105948 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.04628742 = queryNorm
                0.25239927 = fieldWeight in 1717, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=1717)
          0.5 = coord(1/2)
      0.4 = coord(2/5)
    
    Content
    Beitrag für die Tagung: Beyond libraries - subject metadata in the digital environment and semantic web. IFLA Satellite Post-Conference, 17-18 August 2012, Tallinn. Vgl.: http://http://www.nlib.ee/index.php?id=17763.
  4. Kiros, R.; Salakhutdinov, R.; Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models (2014) 0.01
    0.010609357 = product of:
      0.05304678 = sum of:
        0.05304678 = weight(_text_:semantic in 1871) [ClassicSimilarity], result of:
          0.05304678 = score(doc=1871,freq=2.0), product of:
            0.19245663 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.04628742 = queryNorm
            0.2756298 = fieldWeight in 1871, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.046875 = fieldNorm(doc=1871)
      0.2 = coord(1/5)
    
  5. Mao, J.; Xu, W.; Yang, Y.; Wang, J.; Yuille, A.L.: Explain images with multimodal recurrent neural networks (2014) 0.01
    0.007941282 = product of:
      0.03970641 = sum of:
        0.03970641 = weight(_text_:retrieval in 1557) [ClassicSimilarity], result of:
          0.03970641 = score(doc=1557,freq=4.0), product of:
            0.14001551 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.04628742 = queryNorm
            0.2835858 = fieldWeight in 1557, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.046875 = fieldNorm(doc=1557)
      0.2 = coord(1/5)
    
    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.
  6. Gödert, W.: Detecting multiword phrases in mathematical text corpora (2012) 0.01
    0.007487112 = product of:
      0.03743556 = sum of:
        0.03743556 = weight(_text_:retrieval in 466) [ClassicSimilarity], result of:
          0.03743556 = score(doc=466,freq=2.0), product of:
            0.14001551 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.04628742 = queryNorm
            0.26736724 = fieldWeight in 466, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.0625 = fieldNorm(doc=466)
      0.2 = coord(1/5)
    
    Abstract
    We present an approach for detecting multiword phrases in mathematical text corpora. The method used is based on characteristic features of mathematical terminology. It makes use of a software tool named Lingo which allows to identify words by means of previously defined dictionaries for specific word classes as adjectives, personal names or nouns. The detection of multiword groups is done algorithmically. Possible advantages of the method for indexing and information retrieval and conclusions for applying dictionary-based methods of automatic indexing instead of stemming procedures are discussed.
  7. Donahue, J.; Hendricks, L.A.; Guadarrama, S.; Rohrbach, M.; Venugopalan, S.; Saenko, K.; Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description (2014) 0.00
    0.004679445 = product of:
      0.023397226 = sum of:
        0.023397226 = weight(_text_:retrieval in 1873) [ClassicSimilarity], result of:
          0.023397226 = score(doc=1873,freq=2.0), product of:
            0.14001551 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.04628742 = queryNorm
            0.16710453 = fieldWeight in 1873, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1873)
      0.2 = coord(1/5)
    
    Abstract
    Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.
  8. Daudaravicius, V.: ¬A framework for keyphrase extraction from scientific journals (2016) 0.00
    0.0038127303 = product of:
      0.019063652 = sum of:
        0.019063652 = product of:
          0.038127303 = sum of:
            0.038127303 = weight(_text_:web in 2930) [ClassicSimilarity], result of:
              0.038127303 = score(doc=2930,freq=2.0), product of:
                0.15105948 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.04628742 = queryNorm
                0.25239927 = fieldWeight in 2930, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.0546875 = fieldNorm(doc=2930)
          0.5 = coord(1/2)
      0.2 = coord(1/5)
    
    Content
    Vortrag, "Semantics, Analytics, Visualisation: Enhancing Scholarly Data Workshop co-located with the 25th International World Wide Web Conference April 11, 2016 - Montreal, Canada", Montreal 2016.
  9. Junger, U.; Schwens, U.: ¬Die inhaltliche Erschließung des schriftlichen kulturellen Erbes auf dem Weg in die Zukunft : Automatische Vergabe von Schlagwörtern in der Deutschen Nationalbibliothek (2017) 0.00
    0.0031356532 = product of:
      0.015678266 = sum of:
        0.015678266 = product of:
          0.031356532 = sum of:
            0.031356532 = weight(_text_:22 in 3780) [ClassicSimilarity], result of:
              0.031356532 = score(doc=3780,freq=2.0), product of:
                0.16209066 = queryWeight, product of:
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.04628742 = queryNorm
                0.19345059 = fieldWeight in 3780, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=3780)
          0.5 = coord(1/2)
      0.2 = coord(1/5)
    
    Date
    19. 8.2017 9:24:22