Skip to main content

Coding Week 7 Meeting

Attendees

  • Gaurav Mishra
  • Vasudev
  • Ayush Bharadwaj
  • Shreya Singh
  • Kaushlendra Pratap Singh
  • Omar AbdelSamea

Discussions

  • Checking results manually and understanding the edge cases.
  • Implementation of the edge cases like no ['DATE'] and only ['ORG'] or ['PERSON'] is present.
  • Setting up the next target for the remaining weeks.
  • Checking up the REGEX on the copyrights to check the validity of the code.
  • Generating the Accuracy score for TP, FP, FN and TN.

Week 7 Progress

  • [Date] needed to be an important entity for copyright recognition but another check for no dates has been implemented to filter across wider results.
  • Ran the algorithm over 100 thousand copyrights and the time period of 21 mints were scored.
  • REGEX validity was checked and it can be used for future clutter removal maybe.
  • Divided the datasets into chunks of 50 and 100 thousand to calculate wider expected results.
  • More reduction and updation to code was done by removing redundancy of (copyright copyright happening in the statements)
  • The dataset also contains human errors and it is impacting our accuracy score for TP as well.
  • Wiki has been Updated

Conclusion and Further Plans

The filter of the copyrights needed to be more secured.