Information Extraction From Automobile Advertisements.ppt

Information Extraction From Automobile Advertisements Nipun Bhatia Rakshit Kumar Shashank Senapaty Problem Definition Craigslist - Rudimentary keyword search. Not a natural way to search for cars. Difficult to efficiently find ads with particular attributes. Want structured search over attributes. Attributes : Make, Model, Price, Year, Mileage, Transmission, PostedBy, Location, Contact Dataset Issues 350 postings from the cars trucks section in Craigslist. Manually annotated with the attributes. System Diagram Feature Selection Features: Title : isPresentLexicon, hasDollar_hasDigit, hasParanthesis, hasDigit, hasApostrophe_hasDigit, PrevLabel, Word Body :isPresentTrLexicon, isPresentOwLexicon, hasDigit_ hasDash, hasDigit_hasDot, hasDigit_ hasParanthesis, Word_Representation, Neighbor Results Body Classifier Title Classifier Example Results Thank You! * * * *