CLMar 17

Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models

arXiv:2603.1671861.3h-index: 10
AI Analysis

This addresses the challenge of explicit linguistic structure prediction in Arabic, a morphologically rich language, but is incremental as it applies existing LLM methods to new tasks.

The study evaluated instruction-tuned large language models on morphosyntactic tagging and dependency parsing for Standard Arabic, finding that proprietary models approach supervised baselines for tagging and become competitive with specialized parsers using retrieval-based in-context learning.

Large language models (LLMs) perform strongly on many NLP tasks, but their ability to produce explicit linguistic structure remains unclear. We evaluate instruction-tuned LLMs on two structured prediction tasks for Standard Arabic: morphosyntactic tagging and labeled dependency parsing. Arabic provides a challenging testbed due to its rich morphology and orthographic ambiguity, which create strong morphology-syntax interactions. We compare zero-shot prompting with retrieval-based in-context learning (ICL) using examples from Arabic treebanks. Results show that prompt design and demonstration selection strongly affect performance: proprietary models approach supervised baselines for feature-level tagging and become competitive with specialized dependency parsers. In raw-text settings, tokenization remains challenging, though retrieval-based ICL improves both parsing and tokenization. Our analysis highlights which aspects of Arabic morphosyntax and syntax LLMs capture reliably and which remain difficult.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes