Search (2 results, page 1 of 1)

  • × author_ss:"Tang, X."
  1. Tang, X.; Chen, L.; Cui, J.; Wei, B.: Knowledge representation learning with entity descriptions, hierarchical types, and textual relations (2019) 0.02 
    0.020599846 = product of:
  0.061799537 = sum of:
    0.061799537 = product of:
      0.092699304 = sum of:
        0.057281278 = weight(_text_:network in 5101) [ClassicSimilarity], result of:
          0.057281278 = score(doc=5101,freq=2.0), product of:
            0.19402927 = queryWeight, product of:
              4.4533744 = idf(docFreq=1398, maxDocs=44218)
              0.043569047 = queryNorm
            0.29521978 = fieldWeight in 5101, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.4533744 = idf(docFreq=1398, maxDocs=44218)
              0.046875 = fieldNorm(doc=5101)
        0.035418026 = weight(_text_:22 in 5101) [ClassicSimilarity], result of:
          0.035418026 = score(doc=5101,freq=2.0), product of:
            0.15257138 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.043569047 = queryNorm
            0.23214069 = fieldWeight in 5101, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046875 = fieldNorm(doc=5101)
      0.6666667 = coord(2/3)
  0.33333334 = coord(1/3)
    Abstract
    Knowledge representation learning methods usually only utilize triple facts, or just consider one kind of extra information. In this paper, we propose a multi-source knowledge representation learning (MKRL) model, which can combine entity descriptions, hierarchical types, and textual relations with triple facts. Specifically, for entity descriptions, a convolutional neural network is used to get representations. For hierarchical type, weighted hierarchy encoders are used to construct the projection matrixes of hierarchical types, and the projection matrix of an entity combines all hierarchical type projection matrixes of the entity with the relation-specific type constrains. For textual relations, a sentence-level attention mechanism is employed to get representations. We evaluate MKRL model on knowledge graph completion task with dataset FB15k-237, and experimental results demonstrate that our model outperforms the state-of-the-art methods, which indicates the effectiveness of multi-source information for knowledge representation.
    Date
    17. 3.2019 13:22:53
  2. Tang, X.; Yang, C.C.; Song, M.: Understanding the evolution of multiple scientific research domains using a content and network approach (2013) 0.01 
    0.00918649 = product of:
  0.02755947 = sum of:
    0.02755947 = product of:
      0.08267841 = sum of:
        0.08267841 = weight(_text_:network in 744) [ClassicSimilarity], result of:
          0.08267841 = score(doc=744,freq=6.0), product of:
            0.19402927 = queryWeight, product of:
              4.4533744 = idf(docFreq=1398, maxDocs=44218)
              0.043569047 = queryNorm
            0.42611307 = fieldWeight in 744, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              4.4533744 = idf(docFreq=1398, maxDocs=44218)
              0.0390625 = fieldNorm(doc=744)
      0.33333334 = coord(1/3)
  0.33333334 = coord(1/3)
    Abstract
    Interdisciplinary research has been attracting more attention in recent decades. In this article, we compare the similarity between scientific research domains and quantifying the temporal similarities of domains. We narrowed our study to three research domains: information retrieval (IR), database (DB), and World Wide Web (W3), because the rapid development of the W3 domain substantially attracted research efforts from both IR and DB domains and introduced new research questions to these two areas. Most existing approaches either employed a content-based technique or a cocitation or coauthorship network-based technique to study the development trend of a research area. In this work, we proposed an effective way to quantify the similarities among different research domains by incorporating content similarity and coauthorship network similarity. Experimental results on DBLP (DataBase systems and Logic Programming) data related to IR, DB, and W3 domains showed that the W3 domain was getting closer to both IR and DB whereas the distance between IR and DB remained relatively constant. In addition, comparing to IR and W3 with the DB domain, the DB domain was more conservative and evolved relatively slower.

Authors