S-E-D-A/SEDA-ML-Summarization

Issues

• Remove requirement for validation/test set in DBN

  #38 opened 11 years ago by jsalhi
  0

• For script indexPDFinSolrCore.sh create new core if one does not exists

  #37 opened 11 years ago by pcannons
  0

• Generalizing features_to_dict.py

  #36 opened 11 years ago by pcannons
  1

• Script to index a general PDF file

  #35 opened 11 years ago by pcannons
  1

• runQueryOnTopic.sh: takes a text input and topic to generate summary on

  #30 opened 11 years ago by hkuhn
  1

• Make data processing for input more memory efficient

  #34 opened 11 years ago by jsalhi
  0

• Enable Solr cores re-loading on restart

  #33 opened 11 years ago by pcannons
  0

• Evaluation of results at the end of trainTopic.sh if available

  #32 opened 11 years ago by pcannons
  2

• Add data/ to .gitignore and make sure load_data creates ../data folder if it is non existent

  #29 opened 11 years ago by pcannons
  0

• SVM Method Comparison

  #12 opened 11 years ago by hkuhn
  0

• trainTopic.sh to run the entire process of training a topic: indexing, RBM training, and evaluation

  #27 opened 11 years ago by pcannons
  0

• Script to run tf query on a single document

  #28 opened 11 years ago by pcannons
  5

• Extending DBN_Symmetric_RBM.py to take queries

  #31 opened 11 years ago by pcannons
  1

• Given tf query, after running topic set through RBM, tokenize the tf query document into arrays of arrays

  #26 opened 11 years ago by pcannons
  2

• Adapt Theano Restricted Boltzmann Machine to SEDA-ML

  #7 opened 11 years ago by pcannons
  0

• Automatically pull Australian dataset

  #24 opened 11 years ago by pcannons
  5

• Generalize load_data.sh to index query and topic set

  #25 opened 11 years ago by pcannons
  2

• Modify SOLR query to obtain term frequencies to feed into the RBM

  #23 opened 11 years ago by pcannons
  5

• Generate the feature vectors input into the RBM

  #6 opened 11 years ago by pcannons
  2

• Extensive Testing

  #19 opened 11 years ago by hkuhn
  2

• Set up Solr indexing of files

  #10 opened 11 years ago by pcannons
  1

• Develop protocol of communication with Text Detection component

  #11 opened 11 years ago by pcannons
  0

• Break down paper components

  #5 opened 11 years ago by pcannons
  0

• Reconstruction validation

  #3 opened 11 years ago by pcannons
  0

• Concepts extraction

  #4 opened 11 years ago by pcannons
  0

• SOLR-Side Prepping for Python Script

  #22 opened 11 years ago by hkuhn
  1

• SOLR-Side Data Formatting

  #21 opened 11 years ago by hkuhn
  1

• Format Data for SOLR

  #20 opened 11 years ago by hkuhn
  0

• 4) Solve the Optimization Problem

  #16 opened 11 years ago by hkuhn
  0

• 3) Calculate importance of every sentence In_t

  #15 opened 11 years ago by hkuhn
  0

• 2) Word Extraction from Importance Matrix AF

  #14 opened 11 years ago by hkuhn
  0

• 1) Calculate Importance Matrix AF

  #13 opened 11 years ago by hkuhn
  1

• Set-up Python environment in vagrant

  #17 opened 11 years ago by pcannons
  0

• Convert set-up to use BLAS for Theano

  #18 opened 11 years ago by pcannons
  0

• Summary generation

  #2 opened 11 years ago by pcannons
  0

• Check if Solr has already been installed when provisioning

  #9 opened 11 years ago by pcannons
  1

• Install Solr with vagrant

  #8 opened 11 years ago by pcannons
  2

• Concepts extraction

  #1 opened 11 years ago by pcannons
  0