Abstract

Predicting Fine-Grained Syntactic Typology from Surface Features

Authors
  • Dingquan Wang (Johns Hopkins University)
  • Jason Eisner (Johns Hopkins University)

Abstract

We show how to predict the basic word-order facts of a novel language given only a corpus of its 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. Although recovering syntactic structure is usually regarded as unsupervised learning, we train our predictor on languages of known structure. It outperforms the state-of-the-art unsupervised learning by a large margin, especially when we augment the training data with many synthetic languages. Full details can be found in http://www.cs.jhu.edu/~jason/papers/#wang-eisner-2017.

Keywords: Syntactic Typology, Supervised learning, Synthetic data

How to Cite:

Wang, D. & Eisner, J., (2018) “Predicting Fine-Grained Syntactic Typology from Surface Features”, Society for Computation in Linguistics 1(1), 227-228. doi: https://doi.org/10.7275/R5F769RV

Downloads:
Download PDF

124 Views

33 Downloads

Published on
01 Jan 2018