Mar 2026· arXiv.org· Vol abs/2603.16718· 0 citations· 67 references
Computer Science
TL;DR
A unified evaluation of LLMs on Arabic morphosyntactic tagging and dependency parsing, covering pre-tokenized, raw-text, and cascaded settings, and compares zero-shot prompting with retrieval-based in-context learning.
Abstract
LLMs perform strongly across NLP, but their ability to produce explicit grammatical analyses remains unclear. Arabic provides a challenging testbed due to its rich morphology and orthographic ambiguity, which create strong morphology-syntax interactions. We present a unified evaluation of LLMs on Arabic morphosyntactic tagging and dependency parsing, covering pre-tokenized, raw-text, and cascaded settings. We compare zero-shot prompting with retrieval-based in-context learning. Relevant demonstrations substantially improve performance. The strongest LLMs approach supervised tagging and parsing systems; however, they require substantial annotated data for demonstration retrieval and considerable computational resources. We make all code and data used in this paper publicly available.
We present edition 2.0 of the PARSEME multilingual corpus annotated for multiword expressions (MWEs), resulting from efforts of the PARSEME community towards universality-driven modeling of idiomaticity. With respect to previous editions, we extend the annotation scope to all syntactic MWE categories: verbal, nominal,...
Agata Savary, Manon Scholivet, C. Ramisch et al.· International Conference on...· 3 citations
This work develops a reproducible pipeline for cleaning, processing, and parsing Thai text under the Universal Dependencies framework and releases a frequency lexicon and CoNLL-U parses in machine-readable formats suitable for both AI-assisted and conventional programmatic analysis.
Attapol T. Rutherford, Papatchol Thientong· 0 citations
YallaMorph is introduced, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations over 600K benchmark entries, which shows that Arabic morphological generation remains difficult.
Mahmoud Reda, Salam Khalifa, Reham M. Marzouk et al.· 0 citations
While Part-of-speech tagging is considered a well-understood task in the literature, most work has focused on indo-european languages with fusional morphology. For low-resource agglutinative languages, such as brazillian indigenous languages, the task is commonly constrained by small annotated corpora, high lexical spa...
Jonas Oliveira Pereira, Lílian Teixeira de Sousa, Marlo Souza· Brazilian Symposium in Infor...· 0 citations
According to the results of the experiments, the models proved suitable for the task at hand: all the models perform above the random-prediction level, and the most powerful ones achieve 80% accuracy, which is comparable to the results of English-language models of the same size.
P. A. Gousyatskaya, N. Loukachevitch· Automatic Documentation and...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comOct 22, 2026
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
