Search (7 results, page 1 of 1)

0.017121121 = product of:
  0.034242243 = sum of:
    0.017165681 = weight(_text_:information in 1012) [ClassicSimilarity], result of:
      0.017165681 = score(doc=1012,freq=8.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.19395474 = fieldWeight in 1012, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1012)
    0.01707656 = product of:
      0.03415312 = sum of:
        0.03415312 = weight(_text_:22 in 1012) [ClassicSimilarity], result of:
          0.03415312 = score(doc=1012,freq=2.0), product of:
            0.17654699 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.050415643 = queryNorm
            0.19345059 = fieldWeight in 1012, 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=1012)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

Abstract

With the wide application of keyphrases in many Information Retrieval (IR) and Natural Language Processing (NLP) tasks, automatic keyphrase prediction has been emerging. However, these statistically important phrases are contributing increasingly less to the related tasks because the end-to-end learning mechanism enables models to learn the important semantic information of the text directly. Similarly, keyphrases are of little help for readers to quickly grasp the paper's main idea because the relationship between the keyphrase and the paper is not explicit to readers. Therefore, we propose to generate keyphrases with specific functions for readers to bridge the semantic gap between them and the information producers, and verify the effectiveness of the keyphrase function for assisting users' comprehension with a user experiment. A controllable keyphrase generation framework (the CKPG) that uses the keyphrase function as a control code to generate categorized keyphrases is proposed and implemented based on Transformer, BART, and T5, respectively. For the Computer Science domain, the Macro-avgs of , , and on the Paper with Code dataset are up to 0.680, 0.535, and 0.558, respectively. Our experimental results indicate the effectiveness of the CKPG models.

Date

22. 6.2023 14:55:20

Source

Journal of the Association for Information Science and Technology. 74(2023) no.7, S.759-774

0.0064371303 = product of:
  0.025748521 = sum of:
    0.025748521 = weight(_text_:information in 98) [ClassicSimilarity], result of:
      0.025748521 = score(doc=98,freq=18.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.2909321 = fieldWeight in 98, product of:
          4.2426405 = tf(freq=18.0), with freq of:
            18.0 = termFreq=18.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=98)
  0.25 = coord(1/4)

Abstract

With the development of Web-based social networks, many personalized tag recommendation approaches based on multi-information have been proposed. Due to the differences in users' preferences, different users care about different kinds of information. In the meantime, different elements within each kind of information are differentially informative for user tagging behaviors. In this context, how to effectively integrate different elements and different information separately becomes a key part of tag recommendation. However, the existing methods ignore this key part. In order to address this problem, we propose a deep neural network for tag recommendation. Specifically, we model two important attentive aspects with a hierarchical attention model. For different user-item pairs, the bottom layered attention network models the influence of different elements on the features representation of the information while the top layered attention network models the attentive scores of different information. To verify the effectiveness of the proposed method, we conduct extensive experiments on two real-world data sets. The results show that using attention network and different kinds of information can significantly improve the performance of the recommendation model, and verify the effectiveness and superiority of our proposed model.

Source

Journal of the Association for Information Science and Technology. 72(2021) no.2, S.173-189

0.0044597755 = product of:
  0.017839102 = sum of:
    0.017839102 = weight(_text_:information in 4457) [ClassicSimilarity], result of:
      0.017839102 = score(doc=4457,freq=6.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.20156369 = fieldWeight in 4457, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.046875 = fieldNorm(doc=4457)
  0.25 = coord(1/4)

Abstract

With increasing digital information availability, semantic web technologies have been employed to construct semantic digital libraries in order to ease information comprehension. The use of semantic web enables users to search or visualize resources in a semantic fashion. Semantic web generation is a key process in semantic digital library construction, which converts metadata of digital resources into semantic web data. Many text mining technologies, such as keyword extraction and clustering, have been proposed to generate semantic web data. However, one important type of metadata in publications, called affiliation, is hard to convert into semantic web data precisely because different authors, who have the same affiliation, often express the affiliation in different ways. To address this issue, this paper proposes a clustering method based on normalized compression distance for the purpose of affiliation disambiguation. The experimental results show that our method is able to identify different affiliations that denote the same institutes. The clustering results outperform the well-known k-means clustering method in terms of average precision, F-measure, entropy, and purity.

Source

Journal of the American Society for Information Science and Technology. 62(2011) no.6, S.1029-1041

0.0042914203 = product of:
  0.017165681 = sum of:
    0.017165681 = weight(_text_:information in 5052) [ClassicSimilarity], result of:
      0.017165681 = score(doc=5052,freq=8.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.19395474 = fieldWeight in 5052, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=5052)
  0.25 = coord(1/4)

Abstract

Computing Semantic Similarity (SS) between concepts is one of the most critical issues in many domains such as Natural Language Processing and Artificial Intelligence. Over the years, several SS measurement methods have been proposed by exploiting different knowledge resources. Wikipedia provides a large domain-independent encyclopedic repository and a semantic network for computing SS between concepts. Traditional feature-based measures rely on linear combinations of different properties with two main limitations, the insufficient information and the loss of semantic information. In this paper, we propose several hybrid SS measurement approaches by using the Information Content (IC) and features of concepts, which avoid the limitations introduced above. Considering integrating discrete properties into one component, we present two models of semantic representation, called CORM and CARM. Then, we compute SS based on these models and take the IC of categories as a supplement of SS measurement. The evaluation, based on several widely used benchmarks and a benchmark developed by ourselves, sustains the intuitions with respect to human judgments. In summary, our approaches are more efficient in determining SS between concepts and have a better human correlation than previous methods such as Word2Vec and NASARI.

Source

Information processing and management. 54(2018) no.6, S.1002-1021

0.0037164795 = product of:
  0.014865918 = sum of:
    0.014865918 = weight(_text_:information in 2877) [ClassicSimilarity], result of:
      0.014865918 = score(doc=2877,freq=6.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.16796975 = fieldWeight in 2877, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2877)
  0.25 = coord(1/4)

Abstract

The Information Content (IC) of a concept is a fundamental dimension in computational linguistics. It enables a better understanding of concept's semantics. In the past, several approaches to compute IC of a concept have been proposed. However, there are some limitations such as the facts of relying on corpora availability, manual tagging, or predefined ontologies and fitting non-dynamic domains in the existing methods. Wikipedia provides a very large domain-independent encyclopedic repository and semantic network for computing IC of concepts with more coverage than usual ontologies. In this paper, we propose some novel methods to IC computation of a concept to solve the shortcomings of existing approaches. The presented methods focus on the IC computation of a concept (i.e., Wikipedia category) drawn from the Wikipedia category structure. We propose several new IC-based measures to compute the semantic similarity between concepts. The evaluation, based on several widely used benchmarks and a benchmark developed in ourselves, sustains the intuitions with respect to human judgments. Overall, some methods proposed in this paper have a good human correlation and constitute some effective ways of determining IC values for concepts and semantic similarity between concepts.

Source

Information processing and management. 53(2017) no.1, S.248-265

0.0025748524 = product of:
  0.01029941 = sum of:
    0.01029941 = weight(_text_:information in 5293) [ClassicSimilarity], result of:
      0.01029941 = score(doc=5293,freq=2.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.116372846 = fieldWeight in 5293, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.046875 = fieldNorm(doc=5293)
  0.25 = coord(1/4)

Source

Journal of the Association for Information Science and Technology. 70(2019) no.7, S.660-674

0.0021457102 = product of:
  0.008582841 = sum of:
    0.008582841 = weight(_text_:information in 2682) [ClassicSimilarity], result of:
      0.008582841 = score(doc=2682,freq=2.0), product of:
        0.08850355 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.050415643 = queryNorm
        0.09697737 = fieldWeight in 2682, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2682)
  0.25 = coord(1/4)

Source

Information processing and management. 51(2015) no.3, S.215-234