Semantic mining: Unsupervised acquisition of multilingual semantic - PowerPoint PPT Presentation

Journée des Doctorants du LIMSI 30/05/2017 Semantic mining: Unsupervised acquisition of multilingual semantic classes from texts Presenter: Zheng ZHANG Supervisors: Pierre ZWEIGENBAUM & Yue MA Research group: ILES Doctoral school: STIC Funding: CSC Date

Distributional hypothesis Distributional hypothesis: Words that occur in the same • contexts tend to have similar meanings (Harris, 1954). Take a word and its contexts: • pomme rouge • pomme délicieuse • … • By looking at a word’s context, one can infer its meaning • 1

Distributional similarity Distributional hypothesis: Words that occur in the same • contexts tend to have similar meanings (Harris, 1954). Take a word and its contexts: • pomme rouge • pomme délicieuse • … • By looking at a word’s context, one can infer its meaning • 1

Multilingual semantic classes pomme Semantic class: A group of words • clustered by using distributional pêche fruits similarity measures. prunelle poire couleurs 2

Multilingual semantic classes FR EN peach pear fruits pomme pêche apple fruits prunelle colors poire couleurs 2

Multilingual semantic classes FR EN peach pear fruits pomme pêche apple fruits prunelle colors poire couleurs 2

Applications: Unknown words “translation” FR EN peach pear fruits pomme pêche apple fruits prunelle colors poire roux couleurs 3

Applications: Unknown words “translation” FR EN peach pear fruits pomme pêche apple fruits prunelle colors poire roux couleurs 3

Applications: Universal classes extraction FR EN peach pear fruits pomme pêche apple fruits prunelle poire Universal class of “fruits” 4

Merci