LLM_IE v0.4.6

Documentation

Changes

• Added allow_overlap_entities parameter to FrameExtractor.extract_frames() method. This allows LLM to output multiple frames with overlapping entity spans. For example, the text below has two "headache" mentions,

  text = "In trial #12345, headache was reported in 5% of patients, while headache was reported in 10% of patients in arm A."

  LLM generated:

  "[
    {"ClinicalTrial": "#12345", "Arm": "A", "AdverseReaction": "headache", "Percentage": "10%"}, 
    {"ClinicalTrial": "#12345", "Arm": "", "AdverseReaction": "headache", "Percentage": "5%"}
  ]"
  

  When allow_overlap_entities=False, the two frames will be the two "headache" mentions:

  [
    {'frame_id': '0', 'start': 17, 'end': 25, 'entity_text': 'headache', 'attr': {'ClinicalTrial': 'trial #12345', 'Arm': 'arm A', 'Percentage': '5%'}}
    {'frame_id': '1', 'start': 64, 'end': 72, 'entity_text': 'headache', 'attr': {'ClinicalTrial': 'trial #12345', 'Arm': 'arm A', 'Percentage': '10%'}}
  ]

  While allow_overlap_entities=True, the two frames will overlap on the first mention:

  [
    {'frame_id': '0', 'start': 17, 'end': 25, 'entity_text': 'headache', 'attr': {'ClinicalTrial': '#12345', 'Arm': 'A', 'Percentage': '10%'}}
    {'frame_id': '1', 'start': 17, 'end': 25, 'entity_text': 'headache', 'attr': {'ClinicalTrial': '#12345', 'Percentage': '5%'}}
  ]

• Fixed UnboundLocalError in extract_async(). The issue happened when input text_content is too short to be sentence tokenized.