janetzki/fact_extraction

Issues

• Extend method documentation

  #58 opened 8 years ago by slayerpart
  0

• Automated deployment

  #94 opened 7 years ago by janetzki
  0

• Filter extracted relations for relations that are not yet present in DBpedia

  #95 opened 7 years ago by janetzki
  0

• Exclude articles with inappropiate entity types from fact extraction

  #93 opened 7 years ago by janetzki
  0

• Dead references in extracted facts (no existing page)

  #92 opened 7 years ago by janetzki
  0

• Format extracted facts according to TextExt requirements

  #91 opened 7 years ago by janetzki
  0

• Too low recall while pattern learning

  #54 opened 7 years ago by janetzki
  1

• Search and compare graph similarity measures

  #51 opened 8 years ago by janetzki
  1

• Automatic pattern optimization

  #52 opened 8 years ago by janetzki
  0

• Redirect alternative spellings

  #72 opened 8 years ago by janetzki
  0

• Pattern matching by means of type statistics

  #87 opened 8 years ago by janetzki
  0

• TaggedSentence cannot parse special characters

  #90 opened 8 years ago by janetzki
  0

• Use relative position of sentence for pattern recognition?

  #81 opened 8 years ago by janetzki
  2

• Heed not only dbo but also yago for type learning and recognition

  #46 opened 8 years ago by janetzki
  3

• Entity names may contain '/'

  #89 opened 8 years ago by janetzki
  0

• Type learning and type cleaning

  #86 opened 8 years ago by janetzki
  0

• Make PatternTool more abstract

  #88 opened 8 years ago by janetzki
  0

• Compute coefficient for sentence position

  #85 opened 8 years ago by janetzki
  0

• Implement Multithreading

  #50 opened 8 years ago by janetzki
  0

• Bar chart shows impossible high text coverage

  #49 opened 8 years ago by janetzki
  0

• Use more than only dbo for ontology

  #75 opened 8 years ago by janetzki
  0

• Sentence tokenization does not consider bulleted lists as delimiters

  #48 opened 8 years ago by janetzki
  0

• Implement Stanford sentence tokenizer

  #83 opened 8 years ago by janetzki
  0

• Heed transitive types of enities

  #53 opened 8 years ago by janetzki
  1

• Perform pattern cleaning independentally from pattern learning

  #74 opened 8 years ago by janetzki
  0

• Implement stemming

  #82 opened 8 years ago by janetzki
  0

• Forbid testing subjects to be used in training

  #73 opened 8 years ago by janetzki
  0

• TaggedSentence does not find multiple word links

  #80 opened 8 years ago by janetzki
  0

• Sentence tokenizer yields extremely long sentences that crash the dependency parser

  #45 opened 8 years ago by janetzki
  0

• Replace string matching in TaggedSentence with Character Offset matching

  #68 opened 8 years ago by janetzki
  0

• Parse escaped HTML characters in Wikipedia Dump properly

  #69 opened 8 years ago by janetzki
  0

• Redirected wikipedia dump contains corrupted Wikimarkup

  #70 opened 8 years ago by janetzki
  0

• Cache articles in wikipedia_connector.py

  #78 opened 8 years ago by janetzki
  0

• Extracted HTML from Wikipedia dump is not clean

  #76 opened 8 years ago by janetzki
  0

• DBpedia knows entities that are not present in the English Wikipedia

  #79 opened 8 years ago by janetzki
  0

• BeautifulSoup mixes up different articles

  #77 opened 8 years ago by janetzki
  3

• Assertion fail: assert link in addresses_of_all_contained_links

  #66 opened 8 years ago by janetzki
  1

• Boost Stanford CoreNLP

  #71 opened 8 years ago by janetzki
  1

• Craft ground truth data for limited pattern validation

  #61 opened 8 years ago by janetzki
  0

• Create poster for presentation

  #67 opened 8 years ago by dominikglandorf
  0

• Extracted sentences from Wikipedia dump are containing markup

  #47 opened 8 years ago by janetzki
  1

• Some DBpedia pages have no corresponding Wikipedia pages

  #64 opened 8 years ago by janetzki
  1

• Faster line counting

  #65 opened 8 years ago by janetzki
  0

• Remove magic numbers

  #60 opened 8 years ago by janetzki
  0

• Entities with Unicode characters are not in the character index

  #63 opened 8 years ago by janetzki
  0

• Make wikipedia dump index lookup faster

  #56 opened 8 years ago by janetzki
  0

• Redirected Wikipedia dump contains \r\n instead of \n

  #62 opened 8 years ago by janetzki
  0

• Create index structure for whole wikipedia dump

  #55 opened 8 years ago by janetzki
  0

• Automatic generation of config.ini from config-default.ini if missing

  #59 opened 8 years ago by janetzki
  0

• Enable / disable type recognition in config.ini

  #57 opened 8 years ago by janetzki
  0