100 likes | 206 Views
Natural Language Processing. Fine Grain Entities Recognition. Background Information. What about? Machine recognition of English words Identify words of interest Why important? Data mining Deploying internet ads, improving automated searching results etc. Basis for future NLP projects.
E N D
Natural Language Processing Fine Grain Entities Recognition
Background Information • What about? • Machine recognition of English words • Identify words of interest • Why important? • Data mining • Deploying internet ads, improving automated searching results etc. • Basis for future NLP projects.
What we want: Existing data: Find relations: President->Politician Politician->Person River->Location • George Washington->President, Politician, Activist • Abraham Lincoln-> President, Legislator, Politician • Mississippi River->River, Location
Principle Goal 1: • Given a context-free word, return all the possible related categories.
Principle Goal 2: • Achieve this goal on large data sets efficiently.
Approach 1: Conditional Probability • If the data suggests that P(Politician|President)>0.9 (or other pre-determined number) • Then we can conclude that any President is a Politician • Calculation:
Approach 2: Random Walk • 6,000 • 3,000 • Activist • Senator
Synonyms • Strongly connect components in the constructed graph can be treated as synonyms
Future work: • Extend the dataset to Wikipedia or the Web • Move from context-independent to context dependent: • Solve ambiguity in natural language • E.g “Michael Jordan” might refer to the basketball player or the Berkeley scholar.
Thank you for attending! • Special Thanks for my mentor: Lev Ratinov • My name: Xiao Cheng • E-mail: cheng88@illinois.edu