Natural Language Understanding with Machine Learned Annotators and Deep Learned Ontologies at Scale
- 1. NATURAL LANGUAGE UNDERSTANDING WITH MACHINE LEARNED ANNOTATORS & DEEP LEARNED ONTOLOGIES AT SCALE Dr. David Talby
- 2. The problem Who needs to be vaccinated? Who fits this clinical trial? Who is at risk for sepsis? Who is getting meds they’re allergic to? Who on this protocol did not have this side effect?
- 3. At the beginning, there was search Scalable & robust Indexing pipeline Tokenizers & analyzers Synonyms, spellers & Auto-suggest File formats & header boosting Rankers, link & reputation boosting
- 4. Then there was semantic search “cheap red prom dresses” “laptops under $500” “italian restaurants near me that deliver” “captain america civil war tonight” “nba scores” Dictionary Based Attribute Extraction Dell - XPS 15.6 4K Ultra HD Touch- Screen Laptop - Intel Core i5 - 8GB Memory - 256GB Solid State Drive - Silver Machine Learned Attribute Extraction If you go for the ambience, you'll be disappointed. If you go for good, inexpensive and authentic Mexican food, then you're in the right place.
- 5. Then, you need to understand language Prescribing sick days due to diagnosis of influenza. Positive Jane complains about flu-like symptoms. Speculative Jane may be experiencing some sort of flu episode. Possible Jane’s RIDT came back negative for influenza. Negative Jane is at high risk for flu if she’s not vaccinated. Conditional Jane’s older brother had the flu last month. Family history Jane had a severe case of flu last year. Patient history
- 6. 1. Language gets complex and domain specific
- 7. Human language is wonderfully nuanced Joe expressed concerns about the risks of bird flu. Nothing Joe shows no signs of stroke, except for numbness. Double Negative Nausea, vomiting and ankle swelling negative. Compound (it gets worse – in reality a lot of text isn’t valid English) Patient denies alcohol abuse. Speculative Allergies: Penicillin, Dust, Sneezing. Compound
- 8. Let’s build this! The input (patient records) The processing framework The output The query engines
- 9. SENTENCE DETECTION SECTION DETECTION TOKENIZER LEMMATIZER STOPWORD REMOVAL NEGATION DETECTION CONDITIONAL SCOPE SPECULATIVE SCOPE DATE NUMBER UNIT QUANITITY CONCEPT EXTRACTION
- 12. 2. you’ll need machine learning early
- 13. Machine learned annotators Grammatical Patterns If … then … Direct Inferences Age < 18 ==> Child Lookups RIDT (lab test) Under-diagnosed conditions Flu Depression Implied by Context relevant labs normal Sometimes, it’s easier to just code an annotation’s business logic But sometimes it’s easier to learn it from examples:
- 15. 3. bootstrap and then expand your vocabulary
- 17. Expanding & updating ontologies Word2Vec
- 18. Let’s build this too!
- 21. Summary: How Summary: Why 1. Language gets complex and domain specific 2. You’ll need machine learning early 3. Bootstrap & then expand your vocabulary Who needs to be vaccinated? Who fits this clinical trial? Who is at risk for sepsis?