Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing

Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing

Tao Meng, Nanyun Peng, and Kai-Wei Chang, in EMNLP, 2019.

[Full Text]

Abstract

Prior work on cross-lingual dependency pars-ing often focuses on capturing the commonal-ities between source and target languages andoverlook the potential to leverage the linguis-tic properties of the target languages to fa-cilitate the transfer. In this paper, we showthat weak supervisions of linguistic knowl-edge for the target languages can improve across-lingual graph-based dependency parsersubstantially. Specifically, we explore severaltypes ofcorpus linguistic statisticsand com-pile them intocorpus-statistics constraintstofacilitate the inference procedure. We proposenew algorithms that adapt two techniques,Lagrangian relaxation and posterior regular-ization, to conduct inference with corpus-statistics constraints. Experiments show thatthe Lagrangian relaxation and posterior reg-ularization techniques improve the perfor-mances on 15 and 17 out of 19 target lan-guages, respectively. The improvements areespecially large for the target languages thathave different word order features from thesource language.

Bib Entry

@inproceedings{meng2019target,
  author = {Meng, Tao and Peng, Nanyun and Chang, Kai-Wei},
  title = {Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing},
  booktitle = {EMNLP},
  year = {2019}
}

Links

• Code