Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning

Dingquan Wang, Jason Eisner


Abstract
We show how to predict the basic word-order facts of a novel language given only a corpus of part-of-speech (POS) sequences. We predict how often direct objects follow their verbs, how often adjectives follow their nouns, and in general the directionalities of all dependency relations. Such typological properties could be helpful in grammar induction. While such a problem is usually regarded as unsupervised learning, our innovation is to treat it as supervised learning, using a large collection of realistic synthetic languages as training data. The supervised learner must identify surface features of a language’s POS sequence (hand-engineered or neural features) that correlate with the language’s deeper structure (latent trees). In the experiment, we show: 1) Given a small set of real languages, it helps to add many synthetic languages to the training data. 2) Our system is robust even when the POS sequences include noise. 3) Our system on this task outperforms a grammar induction baseline by a large margin.
Anthology ID:
Q17-1011
Volume:
Transactions of the Association for Computational Linguistics, Volume 5
Month:
Year:
2017
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
147–161
Language:
URL:
https://aclanthology.org/Q17-1011
DOI:
10.1162/tacl_a_00052
Bibkey:
Cite (ACL):
Dingquan Wang and Jason Eisner. 2017. Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning. Transactions of the Association for Computational Linguistics, 5:147–161.
Cite (Informal):
Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning (Wang & Eisner, TACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/Q17-1011.pdf
Video:
 https://aclanthology.org/Q17-1011.mp4