# Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages

arXiv: https://arxiv.org/abs/2506.07274 · HTML: https://mlsanity.com/paper/2506.07274/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 5 of 5)

- [LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation](https://mlsanity.com/paper/2005.04322/) (2020)
- [Viable Dependency Parsing as Sequence Labeling](https://mlsanity.com/paper/1902.10505/) (2019)
- [Universal Dependency Parsing for Hindi-English Code-switching](https://mlsanity.com/paper/1804.05868/) (2018)
- [Overview of GUA-SPA at IberLEF 2023: Guarani-Spanish Code Switching Analysis](https://mlsanity.com/paper/2309.06163/) (2023)
- [Second language Korean Universal Dependency treebank v1.2: Focus on data augmentation and annotation scheme refinement](https://mlsanity.com/paper/2503.14718/) (2025)

## Built on by (most cited first, 2 of 2)

- [Construction and educational application of a linguistically grounded dependency treebank for Uyghur](https://mlsanity.com/paper/2507.21536/) (2025)
- [Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages](https://mlsanity.com/paper/2602.02182/) (2026)

## Abstract (arXiv)

Code-switching presents a complex challenge for syntactic analysis, especially in low-resource language settings where annotated data is scarce. While recent work has explored the use of large language models (LLMs) for sequence-level tagging, few approaches systematically investigate how well these models capture syntactic structure in code-switched contexts. Moreover, existing parsers trained on monolingual treebanks often fail to generalize to multilingual and mixed-language input. To address this gap, we introduce the BiLingua Parser, an LLM-based annotation pipeline designed to produce Universal Dependencies (UD) annotations for code-switched text. First, we develop a prompt-based framework for Spanish-English and Spanish-Guaran'i data, combining few-shot LLM prompting with expert review. Second, we release two annotated datasets, including the first Spanish-Guaran'i UD-parsed corpus. Third, we conduct a detailed syntactic analysis of switch points across language pairs and communicative contexts. Experimental results show that BiLingua Parser achieves up to 95.29% LAS after expert revision, significantly outperforming prior baselines and multilingual parsers. These results show that LLMs, when carefully guided, can serve as practical tools for bootstrapping syntactic resources in under-resourced, code-switched environments. Data and source code are available at https://github.com/N3mika/ParsingProject