TY - GEN
T1 - Memory-bounded left-corner unsupervised grammar induction on child-directed input
AU - Shain, Cory
AU - Bryce, William
AU - Jin, Lifeng
AU - Krakovna, Victoria
AU - Doshi-Velez, Finale
AU - Miller, Timothy
AU - Schuier, William
AU - Schwartz, Lane
N1 - Publisher Copyright:
© 1963-2018 ACL.
PY - 2016
Y1 - 2016
N2 - This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM). We deploy this algorithm to shed light on the extent to which human language learners can discover hierarchical syntax through distributional statistics alone, by modeling two widely-accepted features of human language acquisition and sentence processing that have not been simultaneously modeled by any existing grammar induction algorithm: (1) a left-corner parsing strategy and (2) limited working memory capacity. To model realistic input to human language learners, we evaluate our system on a corpus of child-directed speech rather than typical newswire corpora. Results beat or closely match those of three competing systems.
AB - This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM). We deploy this algorithm to shed light on the extent to which human language learners can discover hierarchical syntax through distributional statistics alone, by modeling two widely-accepted features of human language acquisition and sentence processing that have not been simultaneously modeled by any existing grammar induction algorithm: (1) a left-corner parsing strategy and (2) limited working memory capacity. To model realistic input to human language learners, we evaluate our system on a corpus of child-directed speech rather than typical newswire corpora. Results beat or closely match those of three competing systems.
UR - http://www.scopus.com/inward/record.url?scp=85054964486&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054964486&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85054964486
SN - 9784879747020
T3 - COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers
SP - 964
EP - 975
BT - COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016
PB - Association for Computational Linguistics, ACL Anthology
T2 - 26th International Conference on Computational Linguistics, COLING 2016
Y2 - 11 December 2016 through 16 December 2016
ER -