Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Intelligent data extraction system using regular expressions |
| Συγγραφείς: |
Hashesh, Ala', Alkhamra, Othman, Salameh, Ahmad, Sayyad, Abdel Salam |
| Έτος έκδοσης: |
2017 |
| Συλλογή: |
FADA - Birzeit University Open Access Repository |
| Θεματικοί όροι: |
Genetic programming (Computer science), Text processing (Computer science), Programming languages (Electronic computers), Electronic data processing, Text editors (Computer programs) |
| Περιγραφή: |
Data is everywhere, but to extract specific information from huge data could be an exhausting process. However, there are many concepts introduced in computer science can be used to make this problem simpler, such as regular expressions. But, generating a regular expression capable of extracting a predefined string from a text is not an everyday task. In this research, Regular Expression are generated using Genetic Programming. The validity and correctness of a regular expression is decided by making it extract a set of positive examples and ignore another set of negative examples. We validate this method with three datasets related to IPv4 address extraction, article title extraction, and HTML Header extraction. The resulting regular expressions achieved very good accuracy of extraction for the given tasks. |
| Τύπος εγγράφου: |
conference object |
| Γλώσσα: |
English |
| Relation: |
http://hdl.handle.net/20.500.11889/4925 |
| Διαθεσιμότητα: |
https://hdl.handle.net/20.500.11889/4925 |
| Αριθμός Καταχώρησης: |
edsbas.FE86E0CF |
| Βάση Δεδομένων: |
BASE |