Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach

TL;DR

This paper presents a delexicalized cross-lingual constituency parser for Middle High German, leveraging modern German resources to achieve effective syntactic analysis without annotated MHG treebanks.

Contribution

It introduces a novel delexicalized transfer approach for ancient languages, demonstrating high performance despite the lack of annotated training data.

Findings

Achieved an F1-score of 67.3% on MHG test set.

Outperformed zero-shot baseline by 28.6 percentage points.

Showed potential for applying cross-lingual methods to other ancient languages.

Abstract

Constituency parsing plays a fundamental role in advancing natural language processing (NLP) tasks. However, training an automatic syntactic analysis system for ancient languages solely relying on annotated parse data is a formidable task due to the inherent challenges in building treebanks for such languages. It demands extensive linguistic expertise, leading to a scarcity of available resources. To overcome this hurdle, cross-lingual transfer techniques which require minimal or even no annotated data for low-resource target languages offer a promising solution. In this study, we focus on building a constituency parser for $\mathbf{M}$iddle $\mathbf{H}$igh $\mathbf{G}$erman ($\mathbf{MHG}$) under realistic conditions, where no annotated MHG treebank is available for training. In our approach, we leverage the linguistic continuity and structural similarity between MHG and $\mathbf{M}$odern $\mathbf{G}$erman ($\mathbf{MG}$), along with the abundance of MG treebank resources. Specifically, by employing the $\mathit{delexicalization}$ method, we train a constituency parser on MG parse datasets and perform cross-lingual transfer to MHG parsing. Our delexicalized constituency parser demonstrates remarkable performance on the MHG test set, achieving an F1-score of 67.3%. It outperforms the best zero-shot cross-lingual baseline by a margin of 28.6% points. These encouraging results underscore the practicality and potential for automatic syntactic analysis in other ancient languages that face similar challenges as MHG.