DeepAI AI Chat
Log In Sign Up

Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections

by   Junxian He, et al.
Carnegie Mellon University
University of California, San Diego

Cross-lingual transfer is an effective way to build syntactic analysis tools in low-resource languages. However, transfer is difficult when transferring to typologically distant languages, especially when neither annotated target data nor parallel corpora are available. In this paper, we focus on methods for cross-lingual transfer to distant languages and propose to learn a generative model with a structured prior that utilizes labeled source data and unlabeled target data jointly. The parameters of source model and target model are softly shared through a regularized log likelihood objective. An invertible projection is employed to learn a new interlingual latent embedding space that compensates for imperfect cross-lingual word embedding input. We evaluate our method on two syntactic tasks: part-of-speech (POS) tagging and dependency parsing. On the Universal Dependency Treebanks, we use English as the only source corpus and transfer to a wide range of target languages. On the 10 languages in this dataset that are distant from English, our method yields an average of 5.2 absolute improvement on POS tagging and 8.3 parsing over a direct transfer method using state-of-the-art discriminative models.


Low-Resource Syntactic Transfer with Unsupervised Source Reordering

We describe a cross-lingual transfer method for dependency parsing that ...

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

Cross-lingual transfer is a leading technique for parsing low-resource l...

Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank

Treebank translation is a promising method for cross-lingual transfer of...

Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization

We present Expected Statistic Regularization (ESR), a novel regularizati...

Near or Far, Wide Range Zero-Shot Cross-Lingual Dependency Parsing

Cross-lingual transfer is the major means toleverage knowledge from high...

Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data

Providing technologies to communities or domains where training data is ...

Cross-Lingual Adaptation Using Universal Dependencies

We describe a cross-lingual adaptation method based on syntactic parse t...

Code Repositories


PyTorch implementation of ACL paper

view repo