This is a repository for coursework in Natural Language Processing in CS372, 2020 Spring, KAIST.
Please refer to the link : Course, NLTK Book
Find pairs of expressions that are 'intensity-modifying'.
For example,
Extol, praise highly
Destitute, very poor
Find pairs of words where one word is both 'restricting' and 'intensity-modifying' another word.
For example,
pitch black
dead center
deathly sick
stark contrast
Find sentences that has most occurrence of heteronyms.
Single occurrence of heteronym is also counted.
- Homograph: Same letters, different meaning.
- Heteronym: Among homographs, different pronounciation.
For example,
contains: 'wind(air)' + 'wind(tie)' + 'tear(pull apart)' + 'tear(droplet)'
contains: 'wind(air)' + 'wind(tie)' + 'tear(pull apart)'
...
Extract relations from MEDLINE database. <X, ACTION, Y>
Collect 100 sentences with annotated relations.
Use 80 sentences to train, test module with remaining 20 sentences.
For example,
Inorganic phosphate inhibited HPr kinase but activated HPR phosphatase.
=> <Inorganic phosphate, inhibited, HPr kinase>
=> <Inorganic phosphate, activated, HPR phosphatase>
All vasodilators activated K-Cl cotransport in LK SRBCs and HYZ in VSMCs, and this activation was inhibited by calyculin and genistein, two inhibitors of K-Cl cotransport.
=> <All vasodilators, activated, K-CI cotransport>
=> <All vasodilators, activated, HYZ>
=> <this activation, was inhibited by, calyculin> OR <calyculin, inhibited, this activation>
=> <this activation, was inhibited by, genistein> OR <genistein, inhibited, this activation>
=> <this activation, was inhibited by, two inhibitors> OR <two inhibitors, inhibited, this activation>
Resolve coreferences from GAP coreference dataset.
Find right antecedent names for ambiguous pronouns for each snippet.
Divide searching algorithm into two: snippet-context(only uses given text), and page-context(uses whole context from Wikipedia URL).
For example,
In May, Fujisawa joined Mari Motohashi’s rink as the team’s skip, moving back from Karuizawa to Kitami where she had spent her junior days.
=> ‘Fujisawa’ is ‘TRUE’ and ‘Mari Motohashi’ is ‘FALSE’.
Refer to how to setup here.