Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning
Yes! In the present-day documenting and preserving endangered languages, the application of Large Language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in generating grammatical information for low-resource languages with limited amount of data. We takes Moklen as a case study to evaluate the efficacy of LLMs in producing coherent grammatical rules and lexical entries using only bilingual dictionaries and parallel sentences of the unknown language without building the model from scratch. Our methodology involves organising the existing linguistic data and prompting to efficiently enable to generate formal XLE grammar. Our results demonstrate that LLMs can successfully capture key grammatical structures and lexical information, although challenges such as the potential for English grammatical biases remain. This study highlights the potential of LLMs to enhance language documentation efforts, providing a cost-effective solution for generating linguistic data and contributing to the preservation of endangered languages.
Code (0)
등록된 구현이 없습니다.
Tasks
In-Context LearningSimilar Papers 제목 키워드 기반
Kajal: Extracting Grammar of a Source Code Using Large Language Models
Understanding and extracting the grammar of a domain-specific language (DSL) is crucial for various software engineering tasks; however, manually creating these grammars is time-intensive and error-prone. This paper pres…
Few-Shot LearningPrompt EngineeringCan LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et …
Machine TranslationTranslationTokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but driven by statistics rather than grammar. As …
Discovering Textual Structures: Generative Grammar Induction using Template Trees
Natural language generation provides designers with methods for automatically generating text, e.g. for creating summaries, chatbots and game content. In practise, text generators are often either learned and hard to int…
Text GenerationHyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
Grammar plays a critical role in natural language processing and text/code generation by enabling the definition of syntax, the creation of parsers, and guiding structured outputs. Although large language models (LLMs) d…
Code Generation