Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages

Domain:

natural language processing

Record type:

paper

Creator:

Gua

Fel

Host:

Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood. We evaluate four parsers -- the Biaffine LSTM, Stack-Pointer Network, AfroXLMR-large, and RemBERT -- across ten typologically diverse languages, with a focus on low-resource African languages. We find that the Biaffine LSTM consistently outperforms transformer models in low-resource regimes, with transformers recovering their advantage as training data increases. The crossover falls within a resource range typical of treebanks for under-resourced languages. Morphological complexity (measured via MATTR) emerges as a significant secondary predictor of transformers' relative disadvantage after controlling for corpus size. These results indicate that the Biaffine LSTM may be better suited for syntactic tool development in low-resource regimes until sufficient annotated data is available to leverage the representational capacity of pre-trained transformers.

Visit

arxiv.org

Tasks

dependency parsing parsing

Multilingual Dependency Parsing for Low-Resource African Languages: Case Studies on Bambara, Wolof, and Yoruba

Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages

In cross-lingual dependency annotation projection, information is often lost during transfer because

Impact of Vocabulary Augmentation and Script Transliteration on Cross-Lingual Dependency Parsing in Low-Resource Languages

Pretrained multilingual language models have become a common tool in transferring NLP capabilities t

CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages

Neural dependency parsing has achieved remarkable performance for low resource morphologically rich

Multilingual Dependency Parsing for Low-Resource {A}frican Languages: Case Studies on {B}ambara, {W}olof, and {Y}oruba

This paper describes a methodology for syntactic knowledge transfer between high-resource languages to extremely low-resource languages. The methodology consists in leveraging multilingual BERT self-attention model pretrained on large datasets to develop a multilin

Multilingual Projection for Parsing Truly Low-Resource Languages

We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly