Document (#42056)

Author

Ru, C.
Tang, J.
Li, S.
Xie, S.
Wang, T.

Title

Using semantic similarity to reduce wrong labels in distant supervision for relation extraction

Source

Information processing and management. 54(2018) no.4, S.593-608

Year

2018

Abstract

Distant supervision (DS) has the advantage of automatically generating large amounts of labelled training data and has been widely used for relation extraction. However, there are usually many wrong labels in the automatically labelled data in distant supervision (Riedel, Yao, & McCallum, 2010). This paper presents a novel method to reduce the wrong labels. The proposed method uses the semantic Jaccard with word embedding to measure the semantic similarity between the relation phrase in the knowledge base and the dependency phrases between two entities in a sentence to filter the wrong labels. In the process of reducing wrong labels, the semantic Jaccard algorithm selects a core dependency phrase to represent the candidate relation in a sentence, which can capture features for relation classification and avoid the negative impact from irrelevant term sequences that previous neural network models of relation extraction often suffer. In the process of relation classification, the core dependency phrases are also used as the input of a convolutional neural network (CNN) for relation classification. The experimental results show that compared with the methods using original DS data, the methods using filtered DS data performed much better in relation extraction. It indicates that the semantic similarity based method is effective in reducing wrong labels. The relation extraction performance of the CNN model using the core dependency phrases as input is the best of all, which indicates that using the core dependency phrases as input of CNN is enough to capture the features for relation classification and could avoid negative impact from irrelevant terms.

Content

Vgl.: https://doi.org/10.1016/j.ipm.2018.04.002.

Theme

Semantisches Umfeld in Indexierung u. Retrieval
Automatisches Klassifizieren

Similar documents (author)

1. Zhang, X.; Wang, D.; Tang, Y.; Xiao, Q.: How question type influences knowledge withholding in social Q&A community (2023) 3.21

   3.2107148 = sum of:
     3.2107148 = sum of:
       1.1366 = weight(author_txt:wang in 2069) [ClassicSimilarity], result of:
         1.1366 = score(doc=2069,freq=1.0), product of:
           0.5564169 = queryWeight, product of:
             6.5366817 = idf(docFreq=174, maxDocs=44421)
             0.085122235 = queryNorm
           2.042713 = fieldWeight in 2069, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             6.5366817 = idf(docFreq=174, maxDocs=44421)
             0.3125 = fieldNorm(doc=2069)
       2.0741148 = weight(author_txt:tang in 2069) [ClassicSimilarity], result of:
         2.0741148 = score(doc=2069,freq=1.0), product of:
           0.8309032 = queryWeight, product of:
             1.2220107 = boost
             7.9878955 = idf(docFreq=40, maxDocs=44421)
             0.085122235 = queryNorm
           2.4962173 = fieldWeight in 2069, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             7.9878955 = idf(docFreq=40, maxDocs=44421)
             0.3125 = fieldNorm(doc=2069)
   

2. Tang, R.; Solomon, P.: Toward an understanding of the dynamics of relevance judgement : an analysis of one person's search behavior (1998) 1.66

   1.659292 = sum of:
     1.659292 = product of:
       3.318584 = sum of:
         3.318584 = weight(author_txt:tang in 4268) [ClassicSimilarity], result of:
           3.318584 = score(doc=4268,freq=1.0), product of:
             0.8309032 = queryWeight, product of:
               1.2220107 = boost
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.085122235 = queryNorm
             3.9939477 = fieldWeight in 4268, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.5 = fieldNorm(doc=4268)
       0.5 = coord(1/2)
   

3. Tang, R.; Solomon, P.: Use of relevance criteria across stages of document evaluation : on the complementarity of experimental and naturalistic studies (2001) 1.66

   1.659292 = sum of:
     1.659292 = product of:
       3.318584 = sum of:
         3.318584 = weight(author_txt:tang in 213) [ClassicSimilarity], result of:
           3.318584 = score(doc=213,freq=1.0), product of:
             0.8309032 = queryWeight, product of:
               1.2220107 = boost
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.085122235 = queryNorm
             3.9939477 = fieldWeight in 213, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.5 = fieldNorm(doc=213)
       0.5 = coord(1/2)
   

4. Tang, M.-C.: Browsing and searching in a faceted information space : a naturalistic study of PubMed users' interaction with a display tool (2007) 1.66

   1.659292 = sum of:
     1.659292 = product of:
       3.318584 = sum of:
         3.318584 = weight(author_txt:tang in 1617) [ClassicSimilarity], result of:
           3.318584 = score(doc=1617,freq=1.0), product of:
             0.8309032 = queryWeight, product of:
               1.2220107 = boost
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.085122235 = queryNorm
             3.9939477 = fieldWeight in 1617, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.5 = fieldNorm(doc=1617)
       0.5 = coord(1/2)
   

5. Tang, R.; Safer, M.A.: Author-rated importance of cited references in biology and psychology publications (2008) 1.66

   1.659292 = sum of:
     1.659292 = product of:
       3.318584 = sum of:
         3.318584 = weight(author_txt:tang in 2738) [ClassicSimilarity], result of:
           3.318584 = score(doc=2738,freq=1.0), product of:
             0.8309032 = queryWeight, product of:
               1.2220107 = boost
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.085122235 = queryNorm
             3.9939477 = fieldWeight in 2738, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.5 = fieldNorm(doc=2738)
       0.5 = coord(1/2)
   

Similar documents (content)

1. Zhang, M.; Zhou, G.D.; Aw, A.: Exploring syntactic structured features over parse trees for relation extraction using kernel methods (2008) 0.21

   0.21203558 = sum of:
     0.21203558 = product of:
       0.7572699 = sum of:
         0.03559209 = weight(abstract_txt:capture in 3055) [ClassicSimilarity], result of:
           0.03559209 = score(doc=3055,freq=1.0), product of:
             0.08968638 = queryWeight, product of:
               6.3496094 = idf(docFreq=210, maxDocs=44421)
               0.014124708 = queryNorm
             0.3968506 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.3496094 = idf(docFreq=210, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.018988721 = weight(abstract_txt:method in 3055) [ClassicSimilarity], result of:
           0.018988721 = score(doc=3055,freq=1.0), product of:
             0.06753337 = queryWeight, product of:
               1.0627756 = boost
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.014124708 = queryNorm
             0.2811754 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.014358263 = weight(abstract_txt:using in 3055) [ClassicSimilarity], result of:
           0.014358263 = score(doc=3055,freq=1.0), product of:
             0.0664567 = queryWeight, product of:
               1.3610564 = boost
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.014124708 = queryNorm
             0.21605442 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.031138325 = weight(abstract_txt:semantic in 3055) [ClassicSimilarity], result of:
           0.031138325 = score(doc=3055,freq=1.0), product of:
             0.11134421 = queryWeight, product of:
               1.761735 = boost
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.014124708 = queryNorm
             0.27965823 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.2021332 = weight(abstract_txt:extraction in 3055) [ClassicSimilarity], result of:
           0.2021332 = score(doc=3055,freq=6.0), product of:
             0.21322861 = queryWeight, product of:
               2.4379764 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014124708 = queryNorm
             0.94796467 = fieldWeight in 3055, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.18789047 = weight(abstract_txt:dependency in 3055) [ClassicSimilarity], result of:
           0.18789047 = score(doc=3055,freq=1.0), product of:
             0.36904046 = queryWeight, product of:
               3.2073307 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.014124708 = queryNorm
             0.50913244 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.26716885 = weight(abstract_txt:relation in 3055) [ClassicSimilarity], result of:
           0.26716885 = score(doc=3055,freq=5.0), product of:
             0.35493237 = queryWeight, product of:
               4.6654215 = boost
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.014124708 = queryNorm
             0.75273174 = fieldWeight in 3055, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
       0.28 = coord(7/25)
   

2. Vlachidis, A.; Tudhope, D.: ¬A knowledge-based approach to information extraction for semantic interoperability in the archaeology domain (2016) 0.17

   0.16641039 = sum of:
     0.16641039 = product of:
       0.5943228 = sum of:
         0.018988721 = weight(abstract_txt:method in 3895) [ClassicSimilarity], result of:
           0.018988721 = score(doc=3895,freq=1.0), product of:
             0.06753337 = queryWeight, product of:
               1.0627756 = boost
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.014124708 = queryNorm
             0.2811754 = fieldWeight in 3895, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4988065 = idf(docFreq=1342, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.0498944 = weight(abstract_txt:phrase in 3895) [ClassicSimilarity], result of:
           0.0498944 = score(doc=3895,freq=1.0), product of:
             0.11233765 = queryWeight, product of:
               1.1191787 = boost
               7.1063476 = idf(docFreq=98, maxDocs=44421)
               0.014124708 = queryNorm
             0.44414672 = fieldWeight in 3895, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.1063476 = idf(docFreq=98, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.024869243 = weight(abstract_txt:using in 3895) [ClassicSimilarity], result of:
           0.024869243 = score(doc=3895,freq=3.0), product of:
             0.0664567 = queryWeight, product of:
               1.3610564 = boost
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.014124708 = queryNorm
             0.37421724 = fieldWeight in 3895, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.07627301 = weight(abstract_txt:semantic in 3895) [ClassicSimilarity], result of:
           0.07627301 = score(doc=3895,freq=6.0), product of:
             0.11134421 = queryWeight, product of:
               1.761735 = boost
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.014124708 = queryNorm
             0.68501997 = fieldWeight in 3895, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.090283975 = weight(abstract_txt:phrases in 3895) [ClassicSimilarity], result of:
           0.090283975 = score(doc=3895,freq=1.0), product of:
             0.21017188 = queryWeight, product of:
               2.164906 = boost
               6.8731537 = idf(docFreq=124, maxDocs=44421)
               0.014124708 = queryNorm
             0.4295721 = fieldWeight in 3895, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.8731537 = idf(docFreq=124, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.16504106 = weight(abstract_txt:extraction in 3895) [ClassicSimilarity], result of:
           0.16504106 = score(doc=3895,freq=4.0), product of:
             0.21322861 = queryWeight, product of:
               2.4379764 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014124708 = queryNorm
             0.7740099 = fieldWeight in 3895, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
         0.16897242 = weight(abstract_txt:relation in 3895) [ClassicSimilarity], result of:
           0.16897242 = score(doc=3895,freq=2.0), product of:
             0.35493237 = queryWeight, product of:
               4.6654215 = boost
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.014124708 = queryNorm
             0.47606933 = fieldWeight in 3895, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.0625 = fieldNorm(doc=3895)
       0.28 = coord(7/25)
   

3. Agarwal, B.; Ramampiaro, H.; Langseth, H.; Ruocco, M.: ¬A deep network model for paraphrase detection in short text messages (2018) 0.14

   0.13620618 = sum of:
     0.13620618 = product of:
       0.48645064 = sum of:
         0.03559209 = weight(abstract_txt:capture in 43) [ClassicSimilarity], result of:
           0.03559209 = score(doc=43,freq=1.0), product of:
             0.08968638 = queryWeight, product of:
               6.3496094 = idf(docFreq=210, maxDocs=44421)
               0.014124708 = queryNorm
             0.3968506 = fieldWeight in 43, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.3496094 = idf(docFreq=210, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.07738162 = weight(abstract_txt:sentence in 43) [ClassicSimilarity], result of:
           0.07738162 = score(doc=43,freq=3.0), product of:
             0.10436197 = queryWeight, product of:
               1.078718 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.014124708 = queryNorm
             0.7414733 = fieldWeight in 43, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.080171496 = weight(abstract_txt:neural in 43) [ClassicSimilarity], result of:
           0.080171496 = score(doc=43,freq=3.0), product of:
             0.10685554 = queryWeight, product of:
               1.091529 = boost
               6.930783 = idf(docFreq=117, maxDocs=44421)
               0.014124708 = queryNorm
             0.75027925 = fieldWeight in 43, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.930783 = idf(docFreq=117, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.02030565 = weight(abstract_txt:using in 43) [ClassicSimilarity], result of:
           0.02030565 = score(doc=43,freq=2.0), product of:
             0.0664567 = queryWeight, product of:
               1.3610564 = boost
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.014124708 = queryNorm
             0.3055471 = fieldWeight in 43, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.041073095 = weight(abstract_txt:similarity in 43) [ClassicSimilarity], result of:
           0.041073095 = score(doc=43,freq=1.0), product of:
             0.11295172 = queryWeight, product of:
               1.3744495 = boost
               5.8181453 = idf(docFreq=358, maxDocs=44421)
               0.014124708 = queryNorm
             0.36363408 = fieldWeight in 43, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8181453 = idf(docFreq=358, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.04403624 = weight(abstract_txt:semantic in 43) [ClassicSimilarity], result of:
           0.04403624 = score(doc=43,freq=2.0), product of:
             0.11134421 = queryWeight, product of:
               1.761735 = boost
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.014124708 = queryNorm
             0.39549646 = fieldWeight in 43, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
         0.18789047 = weight(abstract_txt:dependency in 43) [ClassicSimilarity], result of:
           0.18789047 = score(doc=43,freq=1.0), product of:
             0.36904046 = queryWeight, product of:
               3.2073307 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.014124708 = queryNorm
             0.50913244 = fieldWeight in 43, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.0625 = fieldNorm(doc=43)
       0.28 = coord(7/25)
   

4. Zhou, G.D.; Zhang, M.: Extracting relation information from text documents by exploring various types of knowledge (2007) 0.13

   0.12583669 = sum of:
     0.12583669 = product of:
       0.6291834 = sum of:
         0.0498944 = weight(abstract_txt:phrase in 1927) [ClassicSimilarity], result of:
           0.0498944 = score(doc=1927,freq=1.0), product of:
             0.11233765 = queryWeight, product of:
               1.1191787 = boost
               7.1063476 = idf(docFreq=98, maxDocs=44421)
               0.014124708 = queryNorm
             0.44414672 = fieldWeight in 1927, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.1063476 = idf(docFreq=98, maxDocs=44421)
               0.0625 = fieldNorm(doc=1927)
         0.014358263 = weight(abstract_txt:using in 1927) [ClassicSimilarity], result of:
           0.014358263 = score(doc=1927,freq=1.0), product of:
             0.0664567 = queryWeight, product of:
               1.3610564 = boost
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.014124708 = queryNorm
             0.21605442 = fieldWeight in 1927, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.4568708 = idf(docFreq=3806, maxDocs=44421)
               0.0625 = fieldNorm(doc=1927)
         0.05393316 = weight(abstract_txt:semantic in 1927) [ClassicSimilarity], result of:
           0.05393316 = score(doc=1927,freq=3.0), product of:
             0.11134421 = queryWeight, product of:
               1.761735 = boost
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.014124708 = queryNorm
             0.48438224 = fieldWeight in 1927, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.0625 = fieldNorm(doc=1927)
         0.21832877 = weight(abstract_txt:extraction in 1927) [ClassicSimilarity], result of:
           0.21832877 = score(doc=1927,freq=7.0), product of:
             0.21322861 = queryWeight, product of:
               2.4379764 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014124708 = queryNorm
             1.0239187 = fieldWeight in 1927, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.0625 = fieldNorm(doc=1927)
         0.29266882 = weight(abstract_txt:relation in 1927) [ClassicSimilarity], result of:
           0.29266882 = score(doc=1927,freq=6.0), product of:
             0.35493237 = queryWeight, product of:
               4.6654215 = boost
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.014124708 = queryNorm
             0.8245763 = fieldWeight in 1927, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.0625 = fieldNorm(doc=1927)
       0.2 = coord(5/25)
   

5. Collovini de Abreu, S.; Vieira, R.: RelP: Portuguese open relation extraction (2017) 0.12

   0.117491774 = sum of:
     0.117491774 = product of:
       0.58745885 = sum of:
         0.010269834 = weight(abstract_txt:data in 4621) [ClassicSimilarity], result of:
           0.010269834 = score(doc=4621,freq=1.0), product of:
             0.049341206 = queryWeight, product of:
               1.0489545 = boost
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.014124708 = queryNorm
             0.20813909 = fieldWeight in 4621, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.3302255 = idf(docFreq=4320, maxDocs=44421)
               0.0625 = fieldNorm(doc=4621)
         0.0446763 = weight(abstract_txt:sentence in 4621) [ClassicSimilarity], result of:
           0.0446763 = score(doc=4621,freq=1.0), product of:
             0.10436197 = queryWeight, product of:
               1.078718 = boost
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.014124708 = queryNorm
             0.42808983 = fieldWeight in 4621, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.849437 = idf(docFreq=127, maxDocs=44421)
               0.0625 = fieldNorm(doc=4621)
         0.031138325 = weight(abstract_txt:semantic in 4621) [ClassicSimilarity], result of:
           0.031138325 = score(doc=4621,freq=1.0), product of:
             0.11134421 = queryWeight, product of:
               1.761735 = boost
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.014124708 = queryNorm
             0.27965823 = fieldWeight in 4621, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.4745317 = idf(docFreq=1375, maxDocs=44421)
               0.0625 = fieldNorm(doc=4621)
         0.14292975 = weight(abstract_txt:extraction in 4621) [ClassicSimilarity], result of:
           0.14292975 = score(doc=4621,freq=3.0), product of:
             0.21322861 = queryWeight, product of:
               2.4379764 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014124708 = queryNorm
             0.6703122 = fieldWeight in 4621, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.0625 = fieldNorm(doc=4621)
         0.35844463 = weight(abstract_txt:relation in 4621) [ClassicSimilarity], result of:
           0.35844463 = score(doc=4621,freq=9.0), product of:
             0.35493237 = queryWeight, product of:
               4.6654215 = boost
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.014124708 = queryNorm
             1.0098956 = fieldWeight in 4621, product of:
               3.0 = tf(freq=9.0), with freq of:
                 9.0 = termFreq=9.0
               5.38611 = idf(docFreq=552, maxDocs=44421)
               0.0625 = fieldNorm(doc=4621)
       0.2 = coord(5/25)