Named Entity Recognition and the Stanford NER Software.ppt

Named Entity Recognition and the Stanford NER Software Jenny Rose Finkel Stanford University March 9, 2007 Named Entity Recognition Germany’s representative to the European Union’s veterinary committee Werner Zwingman said on Wednesday consumers should … Why NER? Question Answering Textual Entailment Coreference Resolution Computational Semantics … NER Data/Bake-Offs CoNLL-2002 and CoNLL-2003 (British newswire) Multiple languages: Spanish, Dutch, English, German 4 entities: Person, Location, Organization, Misc MUC-6 and MUC-7 (American newswire) 7 entities: Person, Location, Organization, Time, Date, Percent, Money ACE 5 entities: Location, Organization, Person, FAC, GPE BBN (Penn Treebank) 22 entities: Animal, Cardinal, Date, Disease, … Hidden Markov Models (HMMs) Generative Find parameters to maximize P(X,Y) Assumes features are independent When labeling Xi future observations are taken into account (forward-backward) MaxEnt Markov Models (MEMMs) Discriminative Find parameters to maximize P(Y|X) No longer assume that features are independent Do not take future observations into account (no forward-backward) Conditional Random Fields (CRFs) Discriminative Doesn’t assume that features are independent When labeling Yi future observations are taken into account ? The best of both worlds! Model Trade-offs Stanford NER CRF Features are more important than model How to train a new model Our Features Word features: current word, previous word, next word, all words within a window Orthographic features: Jenny Xxxx IL-2 XX-# Prefixes and Suffixes: Jenny J, Je, Jen, …, nny, ny, y Label sequences Lots of feature conjunctions Distributional Similarity Features Large, unannotated corpus Each word will appear in contexts - induce a distribution over contexts Cluster words based on how similar their distributions are Use cluster IDs as features Great way to combat sparsity We used Alexander Clark’s distributional similarity code (easy to use,