Document (#40413)

Author

Barrio, P.
Gravano, L.

Title

Sampling strategies for information extraction over the deep web

Source

Information processing and management. 53(2017) no.2, S.309-331

Year

2017

Abstract

Information extraction systems discover structured information in natural language text. Having information in structured form enables much richer querying and data mining than possible over the natural language text. However, information extraction is a computationally expensive task, and hence improving the efficiency of the extraction process over large text collections is of critical interest. In this paper, we focus on an especially valuable family of text collections, namely, the so-called deep-web text collections, whose contents are not crawlable and are only available via querying. Important steps for efficient information extraction over deep-web text collections (e.g., selecting the collections on which to focus the extraction effort, based on their contents; or learning which documents within these collections-and in which order-to process, based on their words and phrases) require having a representative document sample from each collection. These document samples have to be collected by querying the deep-web text collections, an expensive process that renders impractical the existing sampling approaches developed for other data scenarios. In this paper, we systematically study the space of query-based document sampling techniques for information extraction over the deep web. Specifically, we consider (i) alternative query execution schedules, which vary on how they account for the query effectiveness, and (ii) alternative document retrieval and processing schedules, which vary on how they distribute the extraction effort over documents. We report the results of the first large-scale experimental evaluation of sampling techniques for information extraction over the deep web. Our results show the merits and limitations of the alternative query execution and document retrieval and processing strategies, and provide a roadmap for addressing this critically important building block for efficient, scalable information extraction.

Content

Vgl.: http://www.sciencedirect.com/science/article/pii/S0306457316306318 [http://dx.doi.org/10.1016/j.ipm.2016.11.006].

Theme

Internet
Suchtaktik

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

   0.20682643 = sum of:
     0.20682643 = product of:
       0.8617768 = sum of:
         0.0587629 = weight(abstract_txt:structured in 3055) [ClassicSimilarity], result of:
           0.0587629 = score(doc=3055,freq=4.0), product of:
             0.08659765 = queryWeight, product of:
               1.0956106 = boost
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.014560047 = queryNorm
             0.67857385 = fieldWeight in 3055, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.020259958 = weight(abstract_txt:information in 3055) [ClassicSimilarity], result of:
           0.020259958 = score(doc=3055,freq=3.0), product of:
             0.07737133 = queryWeight, product of:
               2.1968453 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.014560047 = queryNorm
             0.26185355 = fieldWeight in 3055, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.04241393 = weight(abstract_txt:text in 3055) [ClassicSimilarity], result of:
           0.04241393 = score(doc=3055,freq=1.0), product of:
             0.16793929 = queryWeight, product of:
               2.8543904 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.014560047 = queryNorm
             0.25255513 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.049091738 = weight(abstract_txt:over in 3055) [ClassicSimilarity], result of:
           0.049091738 = score(doc=3055,freq=1.0), product of:
             0.18513374 = queryWeight, product of:
               2.9969535 = boost
               4.242705 = idf(docFreq=1734, maxDocs=44421)
               0.014560047 = queryNorm
             0.26516905 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.242705 = idf(docFreq=1734, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.15721664 = weight(abstract_txt:deep in 3055) [ClassicSimilarity], result of:
           0.15721664 = score(doc=3055,freq=1.0), product of:
             0.38208798 = queryWeight, product of:
               3.9860754 = boost
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.014560047 = queryNorm
             0.4114671 = fieldWeight in 3055, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.0625 = fieldNorm(doc=3055)
         0.5340317 = weight(abstract_txt:extraction in 3055) [ClassicSimilarity], result of:
           0.5340317 = score(doc=3055,freq=6.0), product of:
             0.56334555 = queryWeight, product of:
               6.248498 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014560047 = 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)
       0.24 = coord(6/25)
   

2. Goh, A.; Hui, S.C.: TES: a text extraction system (1996) 0.20

   0.1972431 = sum of:
     0.1972431 = product of:
       0.82184625 = sum of:
         0.032000702 = weight(abstract_txt:process in 6667) [ClassicSimilarity], result of:
           0.032000702 = score(doc=6667,freq=1.0), product of:
             0.07226068 = queryWeight, product of:
               1.2257441 = boost
               4.048922 = idf(docFreq=2105, maxDocs=44421)
               0.014560047 = queryNorm
             0.44285086 = fieldWeight in 6667, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.048922 = idf(docFreq=2105, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
         0.019877622 = weight(abstract_txt:which in 6667) [ClassicSimilarity], result of:
           0.019877622 = score(doc=6667,freq=1.0), product of:
             0.062371794 = queryWeight, product of:
               1.4701692 = boost
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.014560047 = queryNorm
             0.3186957 = fieldWeight in 6667, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
         0.089978054 = weight(abstract_txt:document in 6667) [ClassicSimilarity], result of:
           0.089978054 = score(doc=6667,freq=2.0), product of:
             0.13546476 = queryWeight, product of:
               2.166638 = boost
               4.29415 = idf(docFreq=1647, maxDocs=44421)
               0.014560047 = queryNorm
             0.6642174 = fieldWeight in 6667, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.29415 = idf(docFreq=1647, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
         0.035454925 = weight(abstract_txt:information in 6667) [ClassicSimilarity], result of:
           0.035454925 = score(doc=6667,freq=3.0), product of:
             0.07737133 = queryWeight, product of:
               2.1968453 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.014560047 = queryNorm
             0.4582437 = fieldWeight in 6667, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
         0.10496912 = weight(abstract_txt:text in 6667) [ClassicSimilarity], result of:
           0.10496912 = score(doc=6667,freq=2.0), product of:
             0.16793929 = queryWeight, product of:
               2.8543904 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.014560047 = queryNorm
             0.6250421 = fieldWeight in 6667, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
         0.5395658 = weight(abstract_txt:extraction in 6667) [ClassicSimilarity], result of:
           0.5395658 = score(doc=6667,freq=2.0), product of:
             0.56334555 = queryWeight, product of:
               6.248498 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014560047 = queryNorm
             0.95778835 = fieldWeight in 6667, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.109375 = fieldNorm(doc=6667)
       0.24 = coord(6/25)
   

3. Rui, Y.; Ortega, M.; Huang, T.S.; Mehrotra, S.: Information retrieval beyond the text document (1999) 0.19

   0.19035207 = sum of:
     0.19035207 = product of:
       0.6798288 = sum of:
         0.04445205 = weight(abstract_txt:efficient in 971) [ClassicSimilarity], result of:
           0.04445205 = score(doc=971,freq=1.0), product of:
             0.09835093 = queryWeight, product of:
               1.1675955 = boost
               5.7852654 = idf(docFreq=370, maxDocs=44421)
               0.014560047 = queryNorm
             0.45197386 = fieldWeight in 971, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7852654 = idf(docFreq=370, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.12543024 = weight(abstract_txt:execution in 971) [ClassicSimilarity], result of:
           0.12543024 = score(doc=971,freq=1.0), product of:
             0.19638973 = queryWeight, product of:
               1.6499188 = boost
               8.175107 = idf(docFreq=33, maxDocs=44421)
               0.014560047 = queryNorm
             0.6386802 = fieldWeight in 971, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.175107 = idf(docFreq=33, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.049347397 = weight(abstract_txt:query in 971) [ClassicSimilarity], result of:
           0.049347397 = score(doc=971,freq=1.0), product of:
             0.13285261 = queryWeight, product of:
               1.9191248 = boost
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.014560047 = queryNorm
             0.37144467 = fieldWeight in 971, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.020677732 = weight(abstract_txt:information in 971) [ClassicSimilarity], result of:
           0.020677732 = score(doc=971,freq=2.0), product of:
             0.07737133 = queryWeight, product of:
               2.1968453 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.014560047 = queryNorm
             0.26725316 = fieldWeight in 971, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.10603482 = weight(abstract_txt:text in 971) [ClassicSimilarity], result of:
           0.10603482 = score(doc=971,freq=4.0), product of:
             0.16793929 = queryWeight, product of:
               2.8543904 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.014560047 = queryNorm
             0.6313878 = fieldWeight in 971, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.061364673 = weight(abstract_txt:over in 971) [ClassicSimilarity], result of:
           0.061364673 = score(doc=971,freq=1.0), product of:
             0.18513374 = queryWeight, product of:
               2.9969535 = boost
               4.242705 = idf(docFreq=1734, maxDocs=44421)
               0.014560047 = queryNorm
             0.3314613 = fieldWeight in 971, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.242705 = idf(docFreq=1734, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
         0.27252188 = weight(abstract_txt:extraction in 971) [ClassicSimilarity], result of:
           0.27252188 = score(doc=971,freq=1.0), product of:
             0.56334555 = queryWeight, product of:
               6.248498 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014560047 = queryNorm
             0.48375618 = fieldWeight in 971, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.078125 = fieldNorm(doc=971)
       0.28 = coord(7/25)
   

4. Suakkaphong, N.; Zhang, Z.; Chen, H.: Disease named entity recognition using semisupervised learning and conditional random fields (2011) 0.19

   0.18995541 = sum of:
     0.18995541 = product of:
       0.6784122 = sum of:
         0.02456253 = weight(abstract_txt:strategies in 367) [ClassicSimilarity], result of:
           0.02456253 = score(doc=367,freq=1.0), product of:
             0.0768492 = queryWeight, product of:
               1.0321026 = boost
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.014560047 = queryNorm
             0.31961986 = fieldWeight in 367, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.113918 = idf(docFreq=725, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.02938145 = weight(abstract_txt:structured in 367) [ClassicSimilarity], result of:
           0.02938145 = score(doc=367,freq=1.0), product of:
             0.08659765 = queryWeight, product of:
               1.0956106 = boost
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.014560047 = queryNorm
             0.33928692 = fieldWeight in 367, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.023394184 = weight(abstract_txt:information in 367) [ClassicSimilarity], result of:
           0.023394184 = score(doc=367,freq=4.0), product of:
             0.07737133 = queryWeight, product of:
               2.1968453 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.014560047 = queryNorm
             0.30236244 = fieldWeight in 367, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.059982352 = weight(abstract_txt:text in 367) [ClassicSimilarity], result of:
           0.059982352 = score(doc=367,freq=2.0), product of:
             0.16793929 = queryWeight, product of:
               2.8543904 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.014560047 = queryNorm
             0.3571669 = fieldWeight in 367, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.16613705 = weight(abstract_txt:sampling in 367) [ClassicSimilarity], result of:
           0.16613705 = score(doc=367,freq=1.0), product of:
             0.346294 = queryWeight, product of:
               3.0984228 = boost
               7.676116 = idf(docFreq=55, maxDocs=44421)
               0.014560047 = queryNorm
             0.47975725 = fieldWeight in 367, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.676116 = idf(docFreq=55, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.06663133 = weight(abstract_txt:collections in 367) [ClassicSimilarity], result of:
           0.06663133 = score(doc=367,freq=1.0), product of:
             0.2269511 = queryWeight, product of:
               3.318206 = boost
               4.6974936 = idf(docFreq=1100, maxDocs=44421)
               0.014560047 = queryNorm
             0.29359335 = fieldWeight in 367, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.6974936 = idf(docFreq=1100, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
         0.3083233 = weight(abstract_txt:extraction in 367) [ClassicSimilarity], result of:
           0.3083233 = score(doc=367,freq=2.0), product of:
             0.56334555 = queryWeight, product of:
               6.248498 = boost
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.014560047 = queryNorm
             0.5473076 = fieldWeight in 367, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.192079 = idf(docFreq=246, maxDocs=44421)
               0.0625 = fieldNorm(doc=367)
       0.28 = coord(7/25)
   

5. Bergamaschi, S.; Domnori, E.; Guerra, F.; Rota, S.; Lado, R.T.; Velegrakis, Y.: Understanding the semantics of keyword queries on relational data without accessing the instance (2012) 0.18

   0.17765355 = sum of:
     0.17765355 = product of:
       0.63447696 = sum of:
         0.02938145 = weight(abstract_txt:structured in 1431) [ClassicSimilarity], result of:
           0.02938145 = score(doc=1431,freq=1.0), product of:
             0.08659765 = queryWeight, product of:
               1.0956106 = boost
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.014560047 = queryNorm
             0.33928692 = fieldWeight in 1431, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.428591 = idf(docFreq=529, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.03556164 = weight(abstract_txt:efficient in 1431) [ClassicSimilarity], result of:
           0.03556164 = score(doc=1431,freq=1.0), product of:
             0.09835093 = queryWeight, product of:
               1.1675955 = boost
               5.7852654 = idf(docFreq=370, maxDocs=44421)
               0.014560047 = queryNorm
             0.3615791 = fieldWeight in 1431, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.7852654 = idf(docFreq=370, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.100344196 = weight(abstract_txt:execution in 1431) [ClassicSimilarity], result of:
           0.100344196 = score(doc=1431,freq=1.0), product of:
             0.19638973 = queryWeight, product of:
               1.6499188 = boost
               8.175107 = idf(docFreq=33, maxDocs=44421)
               0.014560047 = queryNorm
             0.5109442 = fieldWeight in 1431, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.175107 = idf(docFreq=33, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.07895584 = weight(abstract_txt:query in 1431) [ClassicSimilarity], result of:
           0.07895584 = score(doc=1431,freq=4.0), product of:
             0.13285261 = queryWeight, product of:
               1.9191248 = boost
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.014560047 = queryNorm
             0.5943115 = fieldWeight in 1431, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               4.754492 = idf(docFreq=1039, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.09453246 = weight(abstract_txt:querying in 1431) [ClassicSimilarity], result of:
           0.09453246 = score(doc=1431,freq=1.0), product of:
             0.21604373 = queryWeight, product of:
               2.1194327 = boost
               7.000987 = idf(docFreq=109, maxDocs=44421)
               0.014560047 = queryNorm
             0.4375617 = fieldWeight in 1431, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.000987 = idf(docFreq=109, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.023394184 = weight(abstract_txt:information in 1431) [ClassicSimilarity], result of:
           0.023394184 = score(doc=1431,freq=4.0), product of:
             0.07737133 = queryWeight, product of:
               2.1968453 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.014560047 = queryNorm
             0.30236244 = fieldWeight in 1431, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
         0.2723072 = weight(abstract_txt:deep in 1431) [ClassicSimilarity], result of:
           0.2723072 = score(doc=1431,freq=3.0), product of:
             0.38208798 = queryWeight, product of:
               3.9860754 = boost
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.014560047 = queryNorm
             0.7126819 = fieldWeight in 1431, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               6.5834737 = idf(docFreq=166, maxDocs=44421)
               0.0625 = fieldNorm(doc=1431)
       0.28 = coord(7/25)