The Dragon Toolkit
Home Documentation Examples Demos Download Stats Contact

Collective Wisdom based Entity (Concept) Classifier

METHOD: Assignment of a semantic category to an entity (concept) is a challenging problem to machines. Traditional approaches extract features from either surface forms or local contexts (surrounding texts) and then apply machine learning methods or human-coded rules for entity classification. Such classifiers usually require large number of training examples and domain-specific tuning and even human-created ontologies (dictionaries). Instead, this tool utilizes the wisdom of crowds for entity classification. It builds the semantic context for each entity through web search engines such as Google. The top ranked documents returned by a search engine gives the sense of what poeple think of this entity! The new approach is simple, robust and powerful. No tuning, no external dictionaries, applicable to any domain,and most importantly, good accuracy!

DEMO: Three demos are available. The first tells you the PROFESSION of a famous person. The second solves the classic person/location/organization problem. The third distinguish among person, location, organization, animal, plant, food, disease, creative (book, music, software, magzine, movie, law, etc) and product.

HOW: choose the demo in the leftmost drop-down menu and type an entity (concept) name in the middle text field and then click the sbumit button to see the semantic category. Only English language is supported. If the semantic category of your entity is out of the scope of the predefined categorization scheme, it tries to find the closest or most related category.

EXAMPLES: choose famous people, type 'Brad Pitt', it shows ACTOR/ACTRESS. choose P/L/O, type 'Philadelphia Eagles', it shows ORGANIZATION. choose various entities, type 'breast cancer', it shows DISEASE.

Categorization Scheme Entity