Optimizing German Language Tagging with the NEGRA Corpus
Analyzing and improving tag distribution for German text parsing based on NEGRA Corpus data, achieving higher accuracy and reducing errors.
Optimizing German Language Tagging with the NEGRA Corpus
E N D
Presentation Transcript
Parsing the NEGRA corpus Greg Donaker June 14, 2006
NEGRA Corpus • German language tagged corpus • 20,602 sentences (355,096 tokens) • Significantly smaller than Penn Treebank • Can be used similarly to Penn Treebank • Similar annotations, much flatter trees [Dubey & Keller 2003]
Baseline error analysis • Ran through Stanford Parser using NEGRA specific parameters • 91.75% tagging accuracy • PCFG f-score: 66.42 • Most frequently underproposed rule: • NP -> ART NN (98 times) • Most frequently underproposed category: • NN (498 times – three times the next category) • These errors seem abnormally high based on the structure of German language.
Approach • Bug modeled tag distribution of unknown words as baseline distribution • Reworked unknown word model to specifics of German language • Model based on first letter, capitalization of first letter, ending substring of words
Results • Best performing (on both test and validation sets) model matched intuition • Capitalization of first letter, last two characters of word • Improves Tagging accuracy from 91.75% to 94.49% • Improves PCFG F-score from 66.42 to 69.87 • Reduces underproposed NP->ART NN from 98 to 48 • Reduces underproposed NN from 498 to 73