Search (53 results, page 3 of 3)

0.0022989952 = product of:
  0.006896985 = sum of:
    0.006896985 = weight(_text_:a in 3622) [ClassicSimilarity], result of:
      0.006896985 = score(doc=3622,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.13239266 = fieldWeight in 3622, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=3622)
  0.33333334 = coord(1/3)

Abstract

Indexing is contextualized and a brief description is provided of some of the most used automatic indexing systems. We describe SISA, a system which uses location heuristics rules, statistical rules like term frequency (TF) or TF-IDF to obtain automatic or semi-automatic indexing, depending on the user's preference. The aim of this research is to ascertain which rules (location heuristics rules or TF-IDF rules) provide the best indexing terms. SISA is used to obtain the automatic indexing of 200 scientific articles on fruit growing written in Portuguese. It uses, on the one hand, location heuristics rules founded on the value of certain parts of the articles for indexing such as titles, abstracts, keywords, headings, first paragraph, conclusions and references and, on the other, TF-IDF rules. The indexing is then evaluated to ascertain retrieval performance through recall, precision and f-measure. Automatic indexing of the articles with location heuristics rules provided the best results with the evaluation measures.

Type

a

0.002212209 = product of:
  0.0066366266 = sum of:
    0.0066366266 = weight(_text_:a in 2494) [ClassicSimilarity], result of:
      0.0066366266 = score(doc=2494,freq=8.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12739488 = fieldWeight in 2494, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2494)
  0.33333334 = coord(1/3)

Abstract

Tag recommendation strategies that exploit term co-occurrence patterns with tags previously assigned to the target object have consistently produced state-of-the-art results. However, such techniques work only for objects with previously assigned tags. Here we focus on tag recommendation for objects with no tags, a variation of the well-known \textit{cold start} problem. We start by evaluating state-of-the-art co-occurrence based methods in cold start. Our results show that the effectiveness of these methods suffers in this situation. Moreover, we show that employing various automatic filtering strategies to generate an initial tag set that enables the use of co-occurrence patterns produces only marginal improvements. We then propose a new approach that exploits both positive and negative user feedback to iteratively select input tags along with a genetic programming strategy to learn the recommendation function. Our experimental results indicate that extending the methods to include user relevance feedback leads to gains in precision of up to 58% over the best baseline in cold start scenarios and gains of up to 43% over the best baseline in objects that contain some initial tags (i.e., no cold start). We also show that our best relevance-feedback-driven strategy performs well even in scenarios that lack user cooperation (i.e., users may refuse to provide feedback) and user reliability (i.e., users may provide the wrong feedback).

Type

a

0.002212209 = product of:
  0.0066366266 = sum of:
    0.0066366266 = weight(_text_:a in 5045) [ClassicSimilarity], result of:
      0.0066366266 = score(doc=5045,freq=8.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12739488 = fieldWeight in 5045, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5045)
  0.33333334 = coord(1/3)

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.

Type

a

0.0021899752 = product of:
  0.0065699257 = sum of:
    0.0065699257 = weight(_text_:a in 4995) [ClassicSimilarity], result of:
      0.0065699257 = score(doc=4995,freq=4.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12611452 = fieldWeight in 4995, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=4995)
  0.33333334 = coord(1/3)

Abstract

This paper discusses the goals and results of the research project Perseus-a as an attempt to improve information retrieval of digital images by automatically connecting them with text-based descriptions. The development uses the image collection of prometheus, the distributed digital image archive for research and studies, the articles of the digitized Reallexikon zur Deutschen Kunstgeschichte, art historical terminological resources and classification data, and an open source system for linguistic and statistic automatic indexing called lingo.

Type

a

0.0021899752 = product of:
  0.0065699257 = sum of:
    0.0065699257 = weight(_text_:a in 1717) [ClassicSimilarity], result of:
      0.0065699257 = score(doc=1717,freq=4.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12611452 = fieldWeight in 1717, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1717)
  0.33333334 = coord(1/3)

Abstract

The German subject headings authority file (Schlagwortnormdatei/SWD) provides a broad controlled vocabulary for indexing documents of all subjects. Traditionally used for intellectual subject cataloguing primarily of books the Deutsche Nationalbibliothek (DNB, German National Library) has been working on developping and implementing procedures for automated assignment of subject headings for online publications. This project, its results and problems are sketched in the paper.

Type

a

0.0021899752 = product of:
  0.0065699257 = sum of:
    0.0065699257 = weight(_text_:a in 5481) [ClassicSimilarity], result of:
      0.0065699257 = score(doc=5481,freq=4.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12611452 = fieldWeight in 5481, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5481)
  0.33333334 = coord(1/3)

Abstract

This article describes multiple experiments in text mining at Northern Illinois University that were undertaken to improve the efficiency and accuracy of cataloging. It focuses narrowly on subject analysis of dime novels, a format of inexpensive fiction that was popular in the United States between 1860 and 1915. NIU holds more than 55,000 dime novels in its collections, which it is in the process of comprehensively digitizing. Classification, keyword extraction, named-entity recognition, clustering, and topic modeling are discussed as means of assigning subject headings to improve their discoverability by researchers and to increase the productivity of digitization workflows.

Type

a

0.0021899752 = product of:
  0.0065699257 = sum of:
    0.0065699257 = weight(_text_:a in 5909) [ClassicSimilarity], result of:
      0.0065699257 = score(doc=5909,freq=4.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.12611452 = fieldWeight in 5909, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5909)
  0.33333334 = coord(1/3)

Type

a

0.0019158293 = product of:
  0.005747488 = sum of:
    0.005747488 = weight(_text_:a in 1873) [ClassicSimilarity], result of:
      0.005747488 = score(doc=1873,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11032722 = fieldWeight in 1873, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1873)
  0.33333334 = coord(1/3)

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.

Type

a

0.0019158293 = product of:
  0.005747488 = sum of:
    0.005747488 = weight(_text_:a in 3105) [ClassicSimilarity], result of:
      0.005747488 = score(doc=3105,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11032722 = fieldWeight in 3105, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3105)
  0.33333334 = coord(1/3)

Type

a

0.0019158293 = product of:
  0.005747488 = sum of:
    0.005747488 = weight(_text_:a in 4005) [ClassicSimilarity], result of:
      0.005747488 = score(doc=4005,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11032722 = fieldWeight in 4005, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4005)
  0.33333334 = coord(1/3)

Abstract

Subject indexing is an intellectually intensive process that has many inherent uncertainties. Existing manual subject indexing systems generally produce binary outcomes for whether or not to assign an indexing term. This does not sufficiently reflect the extent to which the indexing terms are associated with the documents. On the other hand, the idea of probabilistic or weighted indexing was proposed a long time ago and has seen success in capturing uncertainties in the automatic indexing process. One hurdle to overcome in implementing weighted indexing in manual subject indexing systems is the practical burden that could be added to the already intensive indexing process. This study proposes a method to infer automatically the associations between subject terms and documents through text mining. By uncovering the connections between MeSH descriptors and document text, we are able to derive the weights of MeSH descriptors manually assigned to documents. Our initial results suggest that the inference method is feasible and promising. The study has practical implications for improving subject indexing practice and providing better support for information retrieval.

Type

a

0.0019158293 = product of:
  0.005747488 = sum of:
    0.005747488 = weight(_text_:a in 4292) [ClassicSimilarity], result of:
      0.005747488 = score(doc=4292,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11032722 = fieldWeight in 4292, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4292)
  0.33333334 = coord(1/3)

Abstract

Subject indexing plays an important role in supporting subject access to information resources. Current subject indexing systems do not make adequate distinctions on the importance of assigned subject descriptors. Assigning numeric weights to subject descriptors to distinguish their importance to the documents can strengthen the role of subject metadata. Automated methods are more cost-effective. This study compares different automated weighting methods in different environments. Two evaluation methods were used to assess the performance. Experiments on three datasets in the biomedical domain suggest the performance of different weighting methods depends on whether it is an abstract or full text environment. Mutual information with bag-of-words representation shows the best average performance in the full text environment, while cosine with bag-of-words representation is the best in an abstract environment. The cosine measure has relatively consistent and robust performance. A direct weighting method, IDF (Inverse Document Frequency), can produce quick and reasonable estimates of the weights. Bag-of-words representation generally outperforms the concept-based representation. Further improvement in performance can be obtained by using the learning-to-rank method to integrate different weighting methods. This study follows up Lu and Mao (Journal of the Association for Information Science and Technology, 66, 1776-1784, 2015), in which an automated weighted subject indexing method was proposed and validated. The findings from this study contribute to more effective weighted subject indexing.

Type

a

0.0019158293 = product of:
  0.005747488 = sum of:
    0.005747488 = weight(_text_:a in 5268) [ClassicSimilarity], result of:
      0.005747488 = score(doc=5268,freq=6.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.11032722 = fieldWeight in 5268, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5268)
  0.33333334 = coord(1/3)

Abstract

Automatic subject indexing addresses problems of scale and sustainability and can be at the same time used to enrich existing metadata records, establish more connections across and between resources from various metadata and resource collec-tions, and enhance consistency of the metadata. In this work, au-tomatic subject indexing focuses on assigning index terms or classes from established knowledge organization systems (KOSs) for subject indexing like thesauri, subject headings systems and classification systems. The following major approaches are dis-cussed, in terms of their similarities and differences, advantages and disadvantages for automatic assigned indexing from KOSs: "text categorization," "document clustering," and "document classification." Text categorization is perhaps the most wide-spread, machine-learning approach with what seems generally good reported performance. Document clustering automatically both creates groups of related documents and extracts names of subjects depicting the group at hand. Document classification re-uses the intellectual effort invested into creating a KOS for sub-ject indexing and even simple string-matching algorithms have been reported to achieve good results, because one concept can be described using a number of different terms, including equiv-alent, related, narrower and broader terms. Finally, applicability of automatic subject indexing to operative information systems and challenges of evaluation are outlined, suggesting the need for more research.

Type

a

0.0015485462 = product of:
  0.0046456386 = sum of:
    0.0046456386 = weight(_text_:a in 4310) [ClassicSimilarity], result of:
      0.0046456386 = score(doc=4310,freq=2.0), product of:
        0.05209492 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.045180224 = queryNorm
        0.089176424 = fieldWeight in 4310, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=4310)
  0.33333334 = coord(1/3)

Type

a