Paper: Shallow Parsing With Conditional Random Fields

ACL ID N03-1028
Title Shallow Parsing With Conditional Random Fields
Venue Human Language Technologies
Session Main Conference
Year 2003

Conditional random elds for sequence label- ing offer advantages over both generative mod- els like HMMs and classi ers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the devel- opment of standard evaluation datasets and ex- tensive comparison among methods. We show here how to train a conditional random eld to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported sin- gle model. Improved training methods based on modern optimization algorithms were crit- ical in achieving these results. We present ex- tensive comparisons between models and train- ing methods that con rm and strengthen pre- vious results on shallow parsing and tr...