Document (#39642)

Author
Kim, H.H.
Kim, Y.H.
Title
Generic speech summarization of transcribed lecture videos : using tags and their semantic relations
Source
Journal of the Association for Information Science and Technology. 67(2016) no.2, S.366-379
Year
2016
Abstract
We propose a tag-based framework that simulates human abstractors' ability to select significant sentences based on key concepts in a sentence as well as the semantic relations between key concepts to create generic summaries of transcribed lecture videos. The proposed extractive summarization method uses tags (viewer- and author-assigned terms) as key concepts. Our method employs Flickr tag clusters and WordNet synonyms to expand tags and detect the semantic relations between tags. This method helps select sentences that have a greater number of semantically related key concepts. To investigate the effectiveness and uniqueness of the proposed method, we compare it with an existing technique, latent semantic analysis (LSA), using intrinsic and extrinsic evaluations. The results of intrinsic evaluation show that the tag-based method is as or more effective than the LSA method. We also observe that in the extrinsic evaluation, the grand mean accuracy score of the tag-based method is higher than that of the LSA method, with a statistically significant difference. Elaborating on our results, we discuss the theoretical and practical implications of our findings for speech video summarization and retrieval.
Content
Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23391/abstract.
Theme
Automatisches Abstracting
Form
Videos
Object
Latent Semantic Analysis

Similar documents (content)

  1. Lee, J.-H.; Park, S.; Ahn, C.-M.; Kim, D.: Automatic generic document summarization based on non-negative matrix factorization (2009) 0.29
    0.28724137 = sum of:
      0.28724137 = product of:
        1.025862 = sum of:
          0.037194397 = weight(abstract_txt:proposed in 4449) [ClassicSimilarity], result of:
            0.037194397 = score(doc=4449,freq=1.0), product of:
              0.0847666 = queryWeight, product of:
                1.0394545 = boost
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.017423596 = queryNorm
              0.43878603 = fieldWeight in 4449, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.089586385 = weight(abstract_txt:select in 4449) [ClassicSimilarity], result of:
            0.089586385 = score(doc=4449,freq=1.0), product of:
              0.1523121 = queryWeight, product of:
                1.3933502 = boost
                6.273882 = idf(docFreq=214, maxDocs=41962)
                0.017423596 = queryNorm
              0.5881764 = fieldWeight in 4449, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.273882 = idf(docFreq=214, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.13499926 = weight(abstract_txt:generic in 4449) [ClassicSimilarity], result of:
            0.13499926 = score(doc=4449,freq=2.0), product of:
              0.1588976 = queryWeight, product of:
                1.4231535 = boost
                6.4080777 = idf(docFreq=187, maxDocs=41962)
                0.017423596 = queryNorm
              0.8495991 = fieldWeight in 4449, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.4080777 = idf(docFreq=187, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.17819795 = weight(abstract_txt:sentences in 4449) [ClassicSimilarity], result of:
            0.17819795 = score(doc=4449,freq=2.0), product of:
              0.19120455 = queryWeight, product of:
                1.5611413 = boost
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.017423596 = queryNorm
              0.9319755 = fieldWeight in 4449, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.066540405 = weight(abstract_txt:semantic in 4449) [ClassicSimilarity], result of:
            0.066540405 = score(doc=4449,freq=1.0), product of:
              0.15738863 = queryWeight, product of:
                2.0030637 = boost
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.017423596 = queryNorm
              0.4227777 = fieldWeight in 4449, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.28332493 = weight(abstract_txt:summarization in 4449) [ClassicSimilarity], result of:
            0.28332493 = score(doc=4449,freq=2.0), product of:
              0.29816043 = queryWeight, product of:
                2.3876119 = boost
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.017423596 = queryNorm
              0.9502432 = fieldWeight in 4449, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
          0.23601872 = weight(abstract_txt:method in 4449) [ClassicSimilarity], result of:
            0.23601872 = score(doc=4449,freq=3.0), product of:
              0.31977925 = queryWeight, product of:
                4.037832 = boost
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.017423596 = queryNorm
              0.7380676 = fieldWeight in 4449, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.09375 = fieldNorm(doc=4449)
        0.28 = coord(7/25)
    
  2. Ou, S.; Khoo, S.G.; Goh, D.H.: Automatic multidocument summarization of research abstracts : design and user evaluation (2007) 0.22
    0.21807061 = sum of:
      0.21807061 = product of:
        0.6814707 = sum of:
          0.024796264 = weight(abstract_txt:proposed in 2523) [ClassicSimilarity], result of:
            0.024796264 = score(doc=2523,freq=1.0), product of:
              0.0847666 = queryWeight, product of:
                1.0394545 = boost
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.017423596 = queryNorm
              0.292524 = fieldWeight in 2523, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.018976614 = weight(abstract_txt:that in 2523) [ClassicSimilarity], result of:
            0.018976614 = score(doc=2523,freq=5.0), product of:
              0.056290668 = queryWeight, product of:
                1.3393105 = boost
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.017423596 = queryNorm
              0.3371183 = fieldWeight in 2523, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.042817112 = weight(abstract_txt:based in 2523) [ClassicSimilarity], result of:
            0.042817112 = score(doc=2523,freq=7.0), product of:
              0.08035684 = queryWeight, product of:
                1.4312632 = boost
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.017423596 = queryNorm
              0.5328372 = fieldWeight in 2523, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.11879863 = weight(abstract_txt:sentences in 2523) [ClassicSimilarity], result of:
            0.11879863 = score(doc=2523,freq=2.0), product of:
              0.19120455 = queryWeight, product of:
                1.5611413 = boost
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.017423596 = queryNorm
              0.62131697 = fieldWeight in 2523, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.06321137 = weight(abstract_txt:relations in 2523) [ClassicSimilarity], result of:
            0.06321137 = score(doc=2523,freq=1.0), product of:
              0.1810761 = queryWeight, product of:
                1.8606697 = boost
                5.585397 = idf(docFreq=427, maxDocs=41962)
                0.017423596 = queryNorm
              0.3490873 = fieldWeight in 2523, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.585397 = idf(docFreq=427, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.06664159 = weight(abstract_txt:concepts in 2523) [ClassicSimilarity], result of:
            0.06664159 = score(doc=2523,freq=2.0), product of:
              0.16385667 = queryWeight, product of:
                2.0438082 = boost
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.017423596 = queryNorm
              0.4067066 = fieldWeight in 2523, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.18888327 = weight(abstract_txt:summarization in 2523) [ClassicSimilarity], result of:
            0.18888327 = score(doc=2523,freq=2.0), product of:
              0.29816043 = queryWeight, product of:
                2.3876119 = boost
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.017423596 = queryNorm
              0.63349545 = fieldWeight in 2523, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
          0.15734582 = weight(abstract_txt:method in 2523) [ClassicSimilarity], result of:
            0.15734582 = score(doc=2523,freq=3.0), product of:
              0.31977925 = queryWeight, product of:
                4.037832 = boost
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.017423596 = queryNorm
              0.4920451 = fieldWeight in 2523, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.0625 = fieldNorm(doc=2523)
        0.32 = coord(8/25)
    
  3. Reeve, L.H.; Han, H.; Brooks, A.D.: ¬The use of domain-specific concepts in biomedical text summarization (2007) 0.20
    0.2046257 = sum of:
      0.2046257 = product of:
        0.73080605 = sum of:
          0.014699221 = weight(abstract_txt:that in 2956) [ClassicSimilarity], result of:
            0.014699221 = score(doc=2956,freq=3.0), product of:
              0.056290668 = queryWeight, product of:
                1.3393105 = boost
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.017423596 = queryNorm
              0.2611307 = fieldWeight in 2956, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.016183348 = weight(abstract_txt:based in 2956) [ClassicSimilarity], result of:
            0.016183348 = score(doc=2956,freq=1.0), product of:
              0.08035684 = queryWeight, product of:
                1.4312632 = boost
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.017423596 = queryNorm
              0.20139354 = fieldWeight in 2956, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.11879863 = weight(abstract_txt:sentences in 2956) [ClassicSimilarity], result of:
            0.11879863 = score(doc=2956,freq=2.0), product of:
              0.19120455 = queryWeight, product of:
                1.5611413 = boost
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.017423596 = queryNorm
              0.62131697 = fieldWeight in 2956, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.04436027 = weight(abstract_txt:semantic in 2956) [ClassicSimilarity], result of:
            0.04436027 = score(doc=2956,freq=1.0), product of:
              0.15738863 = queryWeight, product of:
                2.0030637 = boost
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.017423596 = queryNorm
              0.2818518 = fieldWeight in 2956, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.04712272 = weight(abstract_txt:concepts in 2956) [ClassicSimilarity], result of:
            0.04712272 = score(doc=2956,freq=1.0), product of:
              0.16385667 = queryWeight, product of:
                2.0438082 = boost
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.017423596 = queryNorm
              0.287585 = fieldWeight in 2956, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.2671213 = weight(abstract_txt:summarization in 2956) [ClassicSimilarity], result of:
            0.2671213 = score(doc=2956,freq=4.0), product of:
              0.29816043 = queryWeight, product of:
                2.3876119 = boost
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.017423596 = queryNorm
              0.89589787 = fieldWeight in 2956, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                7.167183 = idf(docFreq=87, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
          0.2225206 = weight(abstract_txt:method in 2956) [ClassicSimilarity], result of:
            0.2225206 = score(doc=2956,freq=6.0), product of:
              0.31977925 = queryWeight, product of:
                4.037832 = boost
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.017423596 = queryNorm
              0.6958569 = fieldWeight in 2956, product of:
                2.4494898 = tf(freq=6.0), with freq of:
                  6.0 = termFreq=6.0
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.0625 = fieldNorm(doc=2956)
        0.28 = coord(7/25)
    
  4. Lin, M.; Zhang, Z.: Question-driven segmentation of lecture speech text : towards intelligent e-learning systems (2008) 0.19
    0.18669556 = sum of:
      0.18669556 = product of:
        0.66676986 = sum of:
          0.03506721 = weight(abstract_txt:proposed in 3352) [ClassicSimilarity], result of:
            0.03506721 = score(doc=3352,freq=2.0), product of:
              0.0847666 = queryWeight, product of:
                1.0394545 = boost
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.017423596 = queryNorm
              0.4136914 = fieldWeight in 3352, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.0084866 = weight(abstract_txt:that in 3352) [ClassicSimilarity], result of:
            0.0084866 = score(doc=3352,freq=1.0), product of:
              0.056290668 = queryWeight, product of:
                1.3393105 = boost
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.017423596 = queryNorm
              0.15076388 = fieldWeight in 3352, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.022886708 = weight(abstract_txt:based in 3352) [ClassicSimilarity], result of:
            0.022886708 = score(doc=3352,freq=2.0), product of:
              0.08035684 = queryWeight, product of:
                1.4312632 = boost
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.017423596 = queryNorm
              0.28481346 = fieldWeight in 3352, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.16132778 = weight(abstract_txt:speech in 3352) [ClassicSimilarity], result of:
            0.16132778 = score(doc=3352,freq=4.0), product of:
              0.18610299 = queryWeight, product of:
                1.5401739 = boost
                6.9349895 = idf(docFreq=110, maxDocs=41962)
                0.017423596 = queryNorm
              0.8668737 = fieldWeight in 3352, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                6.9349895 = idf(docFreq=110, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.11589671 = weight(abstract_txt:videos in 3352) [ClassicSimilarity], result of:
            0.11589671 = score(doc=3352,freq=2.0), product of:
              0.188078 = queryWeight, product of:
                1.5483248 = boost
                6.9716907 = idf(docFreq=106, maxDocs=41962)
                0.017423596 = queryNorm
              0.6162162 = fieldWeight in 3352, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.9716907 = idf(docFreq=106, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.08400332 = weight(abstract_txt:sentences in 3352) [ClassicSimilarity], result of:
            0.08400332 = score(doc=3352,freq=1.0), product of:
              0.19120455 = queryWeight, product of:
                1.5611413 = boost
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.017423596 = queryNorm
              0.43933746 = fieldWeight in 3352, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.0293994 = idf(docFreq=100, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
          0.23910151 = weight(abstract_txt:lecture in 3352) [ClassicSimilarity], result of:
            0.23910151 = score(doc=3352,freq=4.0), product of:
              0.24191834 = queryWeight, product of:
                1.7560121 = boost
                7.9068503 = idf(docFreq=41, maxDocs=41962)
                0.017423596 = queryNorm
              0.9883563 = fieldWeight in 3352, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                7.9068503 = idf(docFreq=41, maxDocs=41962)
                0.0625 = fieldNorm(doc=3352)
        0.28 = coord(7/25)
    
  5. Ejei, F.; Beheshti, M.S.H.; Rajabi, T.; Ejehi, Z.: Enriching semantic relations of basic sciences ontology (2017) 0.17
    0.17440212 = sum of:
      0.17440212 = product of:
        0.6228647 = sum of:
          0.024796264 = weight(abstract_txt:proposed in 409) [ClassicSimilarity], result of:
            0.024796264 = score(doc=409,freq=1.0), product of:
              0.0847666 = queryWeight, product of:
                1.0394545 = boost
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.017423596 = queryNorm
              0.292524 = fieldWeight in 409, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.680384 = idf(docFreq=1057, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.0084866 = weight(abstract_txt:that in 409) [ClassicSimilarity], result of:
            0.0084866 = score(doc=409,freq=1.0), product of:
              0.056290668 = queryWeight, product of:
                1.3393105 = boost
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.017423596 = queryNorm
              0.15076388 = fieldWeight in 409, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.4122221 = idf(docFreq=10221, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.022886708 = weight(abstract_txt:based in 409) [ClassicSimilarity], result of:
            0.022886708 = score(doc=409,freq=2.0), product of:
              0.08035684 = queryWeight, product of:
                1.4312632 = boost
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.017423596 = queryNorm
              0.28481346 = fieldWeight in 409, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.2222967 = idf(docFreq=4546, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.1896341 = weight(abstract_txt:relations in 409) [ClassicSimilarity], result of:
            0.1896341 = score(doc=409,freq=9.0), product of:
              0.1810761 = queryWeight, product of:
                1.8606697 = boost
                5.585397 = idf(docFreq=427, maxDocs=41962)
                0.017423596 = queryNorm
              1.047262 = fieldWeight in 409, product of:
                3.0 = tf(freq=9.0), with freq of:
                  9.0 = termFreq=9.0
                5.585397 = idf(docFreq=427, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.12546979 = weight(abstract_txt:semantic in 409) [ClassicSimilarity], result of:
            0.12546979 = score(doc=409,freq=8.0), product of:
              0.15738863 = queryWeight, product of:
                2.0030637 = boost
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.017423596 = queryNorm
              0.7971973 = fieldWeight in 409, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                4.509629 = idf(docFreq=1254, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.09424544 = weight(abstract_txt:concepts in 409) [ClassicSimilarity], result of:
            0.09424544 = score(doc=409,freq=4.0), product of:
              0.16385667 = queryWeight, product of:
                2.0438082 = boost
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.017423596 = queryNorm
              0.57517 = fieldWeight in 409, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                4.60136 = idf(docFreq=1144, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
          0.15734582 = weight(abstract_txt:method in 409) [ClassicSimilarity], result of:
            0.15734582 = score(doc=409,freq=3.0), product of:
              0.31977925 = queryWeight, product of:
                4.037832 = boost
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.017423596 = queryNorm
              0.4920451 = fieldWeight in 409, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                4.545318 = idf(docFreq=1210, maxDocs=41962)
                0.0625 = fieldNorm(doc=409)
        0.28 = coord(7/25)