{"id":1689,"date":"2025-06-12T11:50:30","date_gmt":"2025-06-12T09:50:30","guid":{"rendered":"https:\/\/www.cjvt.si\/llm4dh\/?p=1689"},"modified":"2025-06-12T11:51:35","modified_gmt":"2025-06-12T09:51:35","slug":"1689","status":"publish","type":"post","link":"https:\/\/www.cjvt.si\/llm4dh\/en\/advanced-grammatical-analysis-of-multilingual-corpora\/","title":{"rendered":"Advanced grammatical analysis of multilingual corpora"},"content":{"rendered":"

Advanced grammatical analysis of multilingual corpora<\/b><\/h1>\n<\/div><\/section><\/div>\n

By Matej Klemen<\/span><\/h3>\n<\/div><\/section><\/div>\n

In recent times, linguistics has seen a transition from intuition-based research to data-driven approaches, fueled by the advent of large-scale corpora and advanced computational tools.This shift has led to significant new discoveries about language structure and use, particularly in the field of descriptive and comparative grammar analysis.\u00a0<\/span><\/p>\n

However, traditional corpus-based methods remain labour-intensive and often involve the use of a specialised tool or creation of a programming script, adding complexity and requiring additional non-linguistic expertise from the end user. The emergence of LLMs with reasoning capabilities offers an opportunity to simplify the workflow, as well as enhance linguistic analysis, potentially uncovering previously unidentified patterns of language use.<\/span><\/p>\n

As part of the LLM4DH project, we will develop a novel approach to grammatical analysis of multilingual corpora by augmenting state-of-the-art LLMs with the Universal Dependencies (UD) data. The UD initiative (de Marneffe et al. 2021) has created the largest grammatically annotated dataset to date, encompassing treebanks for more than 160 languages worldwide, and has been instrumental in advancing research in linguistic typology (e.g., Levshina 2022) and other grammar-related disciplines. UD focuses on syntactic structure: how words in a sentence are connected and what grammatical roles they play \u2014 like subject, object, modifier, etc. The goal is to enable analysis and comparison of sentence structure across many different languages using the same system of labels and rules.\u00a0<\/span>To illustrate the idea, we will use the question about the (dominant) word order in a language as an example. The goal is to determine the most frequently occurring word order in terms of the <\/span>S<\/b>ubject (e.g., <\/span>I<\/span><\/i>), <\/span>V<\/b>erb (e.g., <\/span>ate<\/span><\/i>), and <\/span>O<\/b>bject (<\/span>a pie<\/span><\/i>). Figure 1 illustrates the contrast between a traditional approach to answering the question and our proposed approach.<\/span><\/p>\n<\/div><\/section><\/div>

<\/div><\/div><\/div><\/div><\/p>\n

Figure 1: A schema illustrating the contrast in answering the dominant word order query using a traditional approach (top) and our proposed approach (bottom). In our system, the data selection and intermediate analysis is done \u201cunder the hood\u201d, saving the user time spent setting up a workflow. However, the intermediate steps performed are also available to the user, enabling their inspection and potential correction.<\/span><\/em><\/p>\n<\/div><\/section><\/div>\n

What we aim to do<\/h3>\n<\/div><\/section><\/div>\n

We will develop an LLM-based system for grammatical analysis of multilingual corpora. Given a user query, the system will automatically determine the steps required to answer the query, and execute them. This involves tasks such as retrieval of relevant examples, performing analysis on relevant examples (extracting patterns), and summarising the results.<\/span><\/p>\n

In the dominant word order example for Slovene:<\/span><\/p>\n