TY - GEN
T1 - Baby SRL
T2 - 12th Conference on Computational Natural Language Learning, CoNLL 2008
AU - Connor, Michael
AU - Gertner, Yael
AU - Fisher, Cynthia
AU - Roth, Dan
PY - 2008
Y1 - 2008
N2 - A fundamental task in sentence comprehension is to assign semantic roles to sentence constituents. The structure-mapping account proposes that children start with a shallow structural analysis of sentences: children treat the number of nouns in the sentence as a cue to its semantic predicateargument structure, and represent language experience in an abstract format that permits rapid generalization to new verbs. In this paper, we tested the consequences of these representational assumptions via experiments with a system for automatic semantic role labeling (SRL), trained on a sample of child-directed speech. When the SRL was presented with representations of sentence structure consisting simply of an ordered set of nouns, it mimicked experimental findings with toddlers, including a striking error found in children. Adding features representing the position of the verb increased accuracy and eliminated the error. We show the SRL system can use incremental knowledge gain to switch from error-prone noun order features to a more accurate representation, demonstrating a possible mechanism for this process in child development.
AB - A fundamental task in sentence comprehension is to assign semantic roles to sentence constituents. The structure-mapping account proposes that children start with a shallow structural analysis of sentences: children treat the number of nouns in the sentence as a cue to its semantic predicateargument structure, and represent language experience in an abstract format that permits rapid generalization to new verbs. In this paper, we tested the consequences of these representational assumptions via experiments with a system for automatic semantic role labeling (SRL), trained on a sample of child-directed speech. When the SRL was presented with representations of sentence structure consisting simply of an ordered set of nouns, it mimicked experimental findings with toddlers, including a striking error found in children. Adding features representing the position of the verb increased accuracy and eliminated the error. We show the SRL system can use incremental knowledge gain to switch from error-prone noun order features to a more accurate representation, demonstrating a possible mechanism for this process in child development.
UR - http://www.scopus.com/inward/record.url?scp=79960119964&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79960119964&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79960119964
SN - 1905593481
SN - 9781905593484
T3 - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
SP - 81
EP - 88
BT - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Y2 - 16 August 2008 through 17 August 2008
ER -