P92-1028 automated approach for deriving relative pronoun disambiguation rules . This approach avoids
P92-1028 we briefly describe the task of relative pronoun disambiguation . Sections 3 and 4 give the details
W96-0211 Figure 2 shows a portion of three relative pronoun disambiguation cases using the baseline case
P92-1028 APPROACH Our method for deriving relative pronoun disambiguation heuristics consists of the following
P92-1028 directly encode information for relative pronoun disambiguation in the grammar . Alternatively
P92-1028 system creates a hierarchy of relative pronoun disambiguation decisions that replace the hand-coded
P92-1028 approach for the acquisition of relative pronoun disambiguation heuristics that duplicates the
W96-0211 1-nearest neighbor CBL algorithm for relative pronoun disambiguation using the baseline case representation
W96-0211 and applies the technique to the relative pronoun disambiguation task . We conclude with a discussion
W99-0611 case-based learning approach for relative pronoun disambiguation . Our clustering approach differs
P92-1028 hierarchy for tasks other than relative pronoun disambiguation . retrieves the most specific
W96-0211 now outperforms the hand-coded relative pronoun disambiguation rules ( 84.2 % vs. 80.5 % ) at
P92-1028 SENTENCES FROM THE CORPUS For the relative pronoun disambiguation task , we used the MUC-3 corpus
P92-1028 training , the resulting hierarchy of relative pronoun disambiguation decisions supplies the antecedent
W96-0211 applied the technique to the task of relative pronoun disambiguation and found that the case-based
P92-1028 relied on handcoded heuristics for relative pronoun disambiguation fmds the correct antecedent 87
P92-1028 employ one of 3 approaches for relative pronoun disambiguation . Systems that use a formal syntactic
C02-1070 noun phrase . ) Rule 7 attempts relative pronoun disambiguation when it finds the three tokens
P92-1028 online corpora . For the task of relative pronoun disambiguation , the automated approach duplicates
W96-0211 set selection to the problem of relative pronoun disambiguation and show that the casebased learning
hide detail