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

TL;DR

This paper introduces a method that uses linguistic properties of target languages as constraints during inference to improve cross-lingual dependency parsing, especially for languages with different word orders.

Contribution

It proposes leveraging linguistic corpus statistics as constraints in inference, utilizing Lagrangian relaxation and posterior regularization techniques for better transfer across languages.

Findings

Improved parsing performance on most target languages.

Significant gains for languages with different word order.

Effective use of linguistic constraints during inference.

Abstract

Prior work on cross-lingual dependency parsing often focuses on capturing the commonalities between source and target languages and overlooks the potential of leveraging linguistic properties of the languages to facilitate the transfer. In this paper, we show that weak supervisions of linguistic knowledge for the target languages can improve a cross-lingual graph-based dependency parser substantially. Specifically, we explore several types of corpus linguistic statistics and compile them into corpus-wise constraints to guide the inference process during the test time. We adapt two techniques, Lagrangian relaxation and posterior regularization, to conduct inference with corpus-statistics constraints. Experiments show that the Lagrangian relaxation and posterior regularization inference improve the performances on 15 and 17 out of 19 target languages, respectively. The improvements are especially significant for target languages that have different word order features from the source language.