Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing
Preprint
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.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Surface Statistics of an Unknown Language Indicate How to Parse ItTransactions of the Association for Computational Linguistics, 2018
- Enriching Word Vectors with Subword InformationTransactions of the Association for Computational Linguistics, 2017
- Many Languages, One ParserTransactions of the Association for Computational Linguistics, 2016
- Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature RepresentationsTransactions of the Association for Computational Linguistics, 2016
- Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing2015