TY - GEN
T1 - Improved parsing for argument-clusters coordination
AU - Ficler, Jessica
AU - Goldberg, Yoav
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Syntactic parsers perform poorly in prediction of Argument-Cluster Coordination (ACC).We change the PTB representation of ACC to be more suitable for learning by a statistical PCFG parser, affecting 125 trees in the training set. Training on the modified trees yields a slight improvement in EVALB scores on sections 22 and 23. The main evaluation is on a corpus of 4th grade science exams, in which ACC structures are prevalent. On this corpus, we obtain an impressive ×2.7 improvement in recovering ACC structures compared to a parser trained on the original PTB trees.
AB - Syntactic parsers perform poorly in prediction of Argument-Cluster Coordination (ACC).We change the PTB representation of ACC to be more suitable for learning by a statistical PCFG parser, affecting 125 trees in the training set. Training on the modified trees yields a slight improvement in EVALB scores on sections 22 and 23. The main evaluation is on a corpus of 4th grade science exams, in which ACC structures are prevalent. On this corpus, we obtain an impressive ×2.7 improvement in recovering ACC structures compared to a parser trained on the original PTB trees.
UR - https://www.scopus.com/pages/publications/85016599640
U2 - 10.18653/v1/p16-2012
DO - 10.18653/v1/p16-2012
M3 - Conference contribution
AN - SCOPUS:85016599640
T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
SP - 72
EP - 76
BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PB - Association for Computational Linguistics (ACL)
T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Y2 - 7 August 2016 through 12 August 2016
ER -