Maybe you have a few seed tuples or a few

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: R, immediately matched the move, spokesman Tim Wagner said Men+on 1 Men+on 2 •  Base syntac+c chunk sequence from one to the other NP NP PP VP NP NP •  Cons+tuent path through the tree from one to the other NP  NP  S  S  NP •  Dependency path Airlines matched Wagner said Dan Jurafsky GazeTeer and trigger word features for rela'on extrac'on •  Trigger list for family: kinship terms •  parent, wife, husband, grandparent, etc. [from WordNet] •  Gazeaeer: •  Lists of useful geo or geopoli+cal words •  Country name list •  Other sub ­en++es Dan Jurafsky American Airlines, a unit of AMR, immediately matched the move, spokesman Tim Wagner said. Dan Jurafsky Classifiers for supervised methods •  Now you can use any classifier you like •  MaxEnt •  Naïve Bayes •  SVM •  ... •  Train it on the training set, tune on the dev set, test on the test set Dan Jurafsky Evalua'on of Supervised Rela'on Extrac'on •  Compute P/R/F1 for each rela+on P= # of correctly extracted relations Total # of extracted relations # of correctly extracted relations R= Total # of gold relations 36 2 PR F1 = P+R Dan Jurafsky Summary: Supervised Rela'on Extrac'on + Can get high accuracies with enough hand ­labeled training data, if test similar enough to training  ­ Labeling a large training set is expensive  ­ Supervised models are briale, don’t generalize well to different genres Relation Extraction Supervised rela+on extrac+on Relation Extraction Semi ­supervised and unsupervised rela+on extrac+on Dan Jurafsky Seed ­based or bootstrapping approaches to rela'on extrac'on •  No training set? Maybe you have: •  A few seed tuples or •  A few high ­precision paaerns •  Can you use those seeds to do something useful? •  Bootstrapping: use the seeds to directly learn to populate a rela+on Dan Jurafsky Rela'on Bootstrapping (Hearst 1992) •  Gather a set of seed pairs that have rela+on R •  Iterate: 1.  Find sentences with these pairs 2.  Look at the context between or around the pair and generalize the context to create paaerns 3.  Use the paaerns for grep for more pairs Dan Jurafsky Bootstrapping •  <Mark Twain, Elmira> Seed tuple •  Grep (google) for the environments of the seed tuple “Mark Twain is buried in Elmira, NY.” X is buried in Y “The grave of Mark Twain is in Elmira” The grave of X is in Y “Elmira is Mark Twain’s final res+ng place” Y is X’s final res+ng place. •  Use those paaerns to grep for new tuples •  Iterate Dan Jurafsky Dipre: Extract <author,book> pairs Brin, Sergei....
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online