Predicate-Argument Structure Divergences in Chinese and English Parallel Sentences and their Impact on Language Transfer

TL;DR

This paper analyzes predicate-argument structure divergences between Chinese and English in parallel sentences, highlighting how linguistic differences impact cross-lingual NLP transfer, especially emphasizing asymmetry in language transfer effectiveness.

Contribution

It provides a detailed categorization of structural divergences in predicate-argument structures and demonstrates their effect on annotation projection in cross-lingual NLP.

Findings

Language transfer is asymmetric between Chinese and English.

Structural divergences significantly affect annotation projection accuracy.

Source language choice influences transfer success.

Abstract

Cross-lingual Natural Language Processing (NLP) has gained significant traction in recent years, offering practical solutions in low-resource settings by transferring linguistic knowledge from resource-rich to low-resource languages. This field leverages techniques like annotation projection and model transfer for language adaptation, supported by multilingual pre-trained language models. However, linguistic divergences hinder language transfer, especially among typologically distant languages. In this paper, we present an analysis of predicate-argument structures in parallel Chinese and English sentences. We explore the alignment and misalignment of predicate annotations, inspecting similarities and differences and proposing a categorization of structural divergences. The analysis and the categorization are supported by a qualitative and quantitative analysis of the results of an annotation projection experiment, in which, in turn, one of the two languages has been used as source language to project annotations into the corresponding parallel sentences. The results of this analysis show clearly that language transfer is asymmetric. An aspect that requires attention when it comes to selecting the source language in transfer learning applications and that needs to be investigated before any scientific claim about cross-lingual NLP is proposed.