Search (42 results, page 1 of 3)

0.038137365 = product of:
  0.07627473 = sum of:
    0.07627473 = product of:
      0.15254946 = sum of:
        0.15254946 = weight(_text_:e.g in 1462) [ClassicSimilarity], result of:
          0.15254946 = score(doc=1462,freq=4.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.65210533 = fieldWeight in 1462, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0625 = fieldNorm(doc=1462)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Early research at the end of the 1950s on computerized indexing used statistical methods based on e.g. frequency, probability, clustering, and relevance. In the 1960s interest began to focus on linguistic analysis and natural language processing e.g. morphological, morphosyntactical, syntactical and semantic analysis. Since the 1980s computerized indexing research has widened to include images, graphics and sound. Examples are given of notable systems developed within each line of approach

0.0243019 = product of:
  0.0486038 = sum of:
    0.0486038 = product of:
      0.0972076 = sum of:
        0.0972076 = weight(_text_:22 in 402) [ClassicSimilarity], result of:
          0.0972076 = score(doc=402,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.61904186 = fieldWeight in 402, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.125 = fieldNorm(doc=402)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Information processing and management. 22(1986) no.6, S.465-476

0.023835853 = product of:
  0.047671705 = sum of:
    0.047671705 = product of:
      0.09534341 = sum of:
        0.09534341 = weight(_text_:e.g in 1873) [ClassicSimilarity], result of:
          0.09534341 = score(doc=1873,freq=4.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.40756583 = fieldWeight in 1873, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1873)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

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.

0.021264162 = product of:
  0.042528324 = sum of:
    0.042528324 = product of:
      0.08505665 = sum of:
        0.08505665 = weight(_text_:22 in 262) [ClassicSimilarity], result of:
          0.08505665 = score(doc=262,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.5416616 = fieldWeight in 262, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.109375 = fieldNorm(doc=262)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

20.10.2000 12:22:23

0.021264162 = product of:
  0.042528324 = sum of:
    0.042528324 = product of:
      0.08505665 = sum of:
        0.08505665 = weight(_text_:22 in 6265) [ClassicSimilarity], result of:
          0.08505665 = score(doc=6265,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.5416616 = fieldWeight in 6265, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.109375 = fieldNorm(doc=6265)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Information outlook. 9(2005) no.8, S.22-23

0.020225393 = product of:
  0.040450785 = sum of:
    0.040450785 = product of:
      0.08090157 = sum of:
        0.08090157 = weight(_text_:e.g in 1871) [ClassicSimilarity], result of:
          0.08090157 = score(doc=1871,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.34583107 = fieldWeight in 1871, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.046875 = fieldNorm(doc=1871)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

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.

0.018226424 = product of:
  0.03645285 = sum of:
    0.03645285 = product of:
      0.0729057 = sum of:
        0.0729057 = weight(_text_:22 in 58) [ClassicSimilarity], result of:
          0.0729057 = score(doc=58,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.46428138 = fieldWeight in 58, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=58)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

14. 6.2015 22:12:44

0.018226424 = product of:
  0.03645285 = sum of:
    0.03645285 = product of:
      0.0729057 = sum of:
        0.0729057 = weight(_text_:22 in 5887) [ClassicSimilarity], result of:
          0.0729057 = score(doc=5887,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.46428138 = fieldWeight in 5887, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=5887)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Wissen in Aktion: Wege des Knowledge Managements. 22. Online-Tagung der DGI, Frankfurt am Main, 2.-4.5.2000. Proceedings. Hrsg.: R. Schmidt

0.018226424 = product of:
  0.03645285 = sum of:
    0.03645285 = product of:
      0.0729057 = sum of:
        0.0729057 = weight(_text_:22 in 2051) [ClassicSimilarity], result of:
          0.0729057 = score(doc=2051,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.46428138 = fieldWeight in 2051, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=2051)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

14. 6.2015 22:12:56

0.018226424 = product of:
  0.03645285 = sum of:
    0.03645285 = product of:
      0.0729057 = sum of:
        0.0729057 = weight(_text_:22 in 5629) [ClassicSimilarity], result of:
          0.0729057 = score(doc=5629,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.46428138 = fieldWeight in 5629, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=5629)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

B.I.T.online. 22(2019) H.2, S.163-166

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 6029) [ClassicSimilarity], result of:
          0.06741798 = score(doc=6029,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 6029, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=6029)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Over the past few years, temporal information processing and temporal database management have increasingly become hot topics. Nevertheless, only a few researchers have investigated these areas in the Chinese language. This lays down the objective of our research: to exploit Chinese language processing techniques for temporal information extraction and concept reasoning. In this article, we first study the mechanism for expressing time in Chinese. On the basis of the study, we then design a general frame structure for maintaining the extracted temporal concepts and propose a system for extracting time-dependent information from Hong Kong financial news. In the system, temporal knowledge is represented by different types of temporal concepts (TTC) and different temporal relations, including absolute and relative relations, which are used to correlate between action times and reference times. In analyzing a sentence, the algorithm first determines the situation related to the verb. This in turn will identify the type of temporal concept associated with the verb. After that, the relevant temporal information is extracted and the temporal relations are derived. These relations link relevant concept frames together in chronological order, which in turn provide the knowledge to fulfill users' queries, e.g., for question-answering (i.e., Q&A) applications

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 963) [ClassicSimilarity], result of:
          0.06741798 = score(doc=963,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 963, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=963)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

In image retrieval, most systems lack user-centred evaluation since they are assessed by some chosen ground truth dataset. The results reported through precision and recall assessed against the ground truth are thought of as being an acceptable surrogate for the judgment of real users. Much current research focuses on automatically assigning keywords to images for enhancing retrieval effectiveness. However, evaluation methods are usually based on system-level assessment, e.g. classification accuracy based on some chosen ground truth dataset. In this paper, we present a qualitative evaluation methodology for automatic image indexing systems. The automatic indexing task is formulated as one of image annotation, or automatic metadata generation for images. The evaluation is composed of two individual methods. First, the automatic indexing annotation results are assessed by human subjects. Second, the subjects are asked to annotate some chosen images as the test set whose annotations are used as ground truth. Then, the system is tested by the test set whose annotation results are judged against the ground truth. Only one of these methods is reported for most systems on which user-centred evaluation are conducted. We believe that both methods need to be considered for full evaluation. We also provide an example evaluation of our system based on this methodology. According to this study, our proposed evaluation methodology is able to provide deeper understanding of the system's performance.

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 1842) [ClassicSimilarity], result of:
          0.06741798 = score(doc=1842,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 1842, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1842)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Many terminology engineering processes involve the task of automatic terminology extraction: before the terminology of a given domain can be modelled, organised or standardised, important concepts (or terms) of this domain have to be identified and fed into terminological databases. These serve in further steps as a starting point for compiling dictionaries, thesauri or maybe even terminological ontologies for the domain. For the extraction of the initial concepts, extraction methods are needed that operate on specialised language texts. On the other hand, many machine learning or information retrieval applications require automatic indexing techniques. In Machine Learning applications concerned with the automatic clustering or classification of texts, often feature vectors are needed that describe the contents of a given text briefly but meaningfully. These feature vectors typically consist of a fairly small set of index terms together with weights indicating their importance. Short but meaningful descriptions of document contents as provided by good index terms are also useful to humans: some knowledge management applications (e.g. topic maps) use them as a set of basic concepts (topics). The author believes that the tasks of terminology extraction and automatic indexing have much in common and can thus benefit from the same set of basic algorithms. It is the goal of this paper to outline some methods that may be used in both contexts, but also to find the discriminating factors between the two tasks that call for the variation of parameters or application of different techniques. The discussion of these methods will be based on statistical, syntactical and especially morphological properties of (index) terms. The paper is concluded by the presentation of some qualitative and quantitative results comparing statistical and morphological methods.

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 5045) [ClassicSimilarity], result of:
          0.06741798 = score(doc=5045,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 5045, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5045)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Topic models often produce unexplainable topics that are filled with noisy words. The reason is that words in topic modeling have equal weights. High frequency words dominate the top topic word lists, but most of them are meaningless words, e.g., domain-specific stopwords. To address this issue, in this paper we aim to investigate how to weight words, and then develop a straightforward but effective term weighting scheme, namely entropy weighting (EW). The proposed EW scheme is based on conditional entropy measured by word co-occurrences. Compared with existing term weighting schemes, the highlight of EW is that it can automatically reward informative words. For more robust word weight, we further suggest a combination form of EW (CEW) with two existing weighting schemes. Basically, our CEW assigns meaningless words lower weights and informative words higher weights, leading to more coherent topics during topic modeling inference. We apply CEW to Dirichlet multinomial mixture and latent Dirichlet allocation, and evaluate it by topic quality, document clustering and classification tasks on 8 real world data sets. Experimental results show that weighting words can effectively improve the topic modeling performance over both short texts and normal long texts. More importantly, the proposed CEW significantly outperforms the existing term weighting schemes, since it further considers which words are informative.

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 5400) [ClassicSimilarity], result of:
          0.06741798 = score(doc=5400,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 5400, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5400)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Automatic subject prediction is a desirable feature for modern digital library systems, as manual indexing can no longer cope with the rapid growth of digital collections. It is also desirable to be able to identify a small set of entities (e.g., authors, citations, bibliographic records) which are most relevant to a query. This gets more difficult when the amount of data increases dramatically. Data sparsity and model scalability are the major challenges to solving this type of extreme multilabel classification problem automatically. In this paper, we propose to address this problem in two steps: we first embed different types of entities into the same semantic space, where similarity could be computed easily; second, we propose a novel non-parametric method to identify the most relevant entities in addition to direct semantic similarities. We show how effectively this approach predicts even very specialised subjects, which are associated with few documents in the training set and are more problematic for a classifier.

0.016854495 = product of:
  0.03370899 = sum of:
    0.03370899 = product of:
      0.06741798 = sum of:
        0.06741798 = weight(_text_:e.g in 1024) [ClassicSimilarity], result of:
          0.06741798 = score(doc=1024,freq=2.0), product of:
            0.23393378 = queryWeight, product of:
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.044842023 = queryNorm
            0.28819257 = fieldWeight in 1024, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.2168427 = idf(docFreq=651, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1024)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

There are several ways to employ machine learning for automating subject indexing. One popular strategy is to utilize a supervised learning algorithm to train a model on a set of documents that have been manually indexed by subject matter using a standard vocabulary. The resulting model can then predict the subject of new and previously unseen documents by identifying patterns learned from the training data. To do this, the first step is to gather a large dataset of documents and manually assign each document a set of subject keywords/descriptors from a controlled vocabulary (e.g., from Agrovoc). Next, the dataset (obtained from Agris) can be divided into - i) a training dataset, and ii) a test dataset. The training dataset is used to train the model, while the test dataset is used to evaluate the model's performance. Machine learning can be a powerful tool for automating the process of subject indexing. This research is an attempt to apply Annif (http://annif. org/), an open-source AI/ML framework, to autogenerate subject keywords/descriptors for documentary resources in the domain of agriculture. The training dataset is obtained from Agris, which applies the Agrovoc thesaurus as a vocabulary tool (https://www.fao.org/agris/download).

0.0151886875 = product of:
  0.030377375 = sum of:
    0.030377375 = product of:
      0.06075475 = sum of:
        0.06075475 = weight(_text_:22 in 1952) [ClassicSimilarity], result of:
          0.06075475 = score(doc=1952,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.38690117 = fieldWeight in 1952, 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=1952)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

16. 8.1998 12:51:22

0.0151886875 = product of:
  0.030377375 = sum of:
    0.030377375 = product of:
      0.06075475 = sum of:
        0.06075475 = weight(_text_:22 in 4157) [ClassicSimilarity], result of:
          0.06075475 = score(doc=4157,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.38690117 = fieldWeight in 4157, 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=4157)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Information und Märkte: 50. Deutscher Dokumentartag 1998, Kongreß der Deutschen Gesellschaft für Dokumentation e.V. (DGD), Rheinische Friedrich-Wilhelms-Universität Bonn, 22.-24. September 1998. Hrsg. von Marlies Ockenfeld u. Gerhard J. Mantwill

0.0151886875 = product of:
  0.030377375 = sum of:
    0.030377375 = product of:
      0.06075475 = sum of:
        0.06075475 = weight(_text_:22 in 374) [ClassicSimilarity], result of:
          0.06075475 = score(doc=374,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = queryNorm
            0.38690117 = fieldWeight in 374, 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=374)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

1. 4.2002 10:22:41

0.0151886875 = product of:
  0.030377375 = sum of:
    0.030377375 = product of:
      0.06075475 = sum of:
        0.06075475 = weight(_text_:22 in 2759) [ClassicSimilarity], result of:
          0.06075475 = score(doc=2759,freq=2.0), product of:
            0.15702912 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.044842023 = 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)
  0.5 = coord(1/2)

Date

1. 2.2016 18:25:22