Hire a linguist!: Learning endangered languages in LLMs with in-context linguistic descriptions
How can large language models (LLMs) process and translate endangered languages?
Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely …
Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely …
Towards multilingual interlinear morphological glossing
S Okabe, F Yvon - 2023 Conference on Empirical Methods in Natural …, 2023 - hal.science
Interlinear Morphological Glosses are annotations produced in the context of language
documentation. Their goal is to identify morphs occurring in an L1 sentence and to explicit …
documentation. Their goal is to identify morphs occurring in an L1 sentence and to explicit …
[PDF][PDF] SigMoreFun submission to the SIGMORPHON shared task on interlinear glossing
In our submission to the SIGMORPHON 2023 Shared Task on interlinear glossing (IGT), we
explore approaches to data augmentation and modeling across seven low-resource …
explore approaches to data augmentation and modeling across seven low-resource …
Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions
How can large language models (LLMs) process and translate endangered languages?
Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely …
Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely …
Glossy bytes: Neural glossing using subword encoding
Z Cross, M Yun, A Apparaju, J MacCabe… - Proceedings of the …, 2023 - aclanthology.org
This paper presents several different neural subword modelling based approaches to
interlinear glossing for seven under-resourced languages as a part of the 2023 …
interlinear glossing for seven under-resourced languages as a part of the 2023 …
Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation
B Shandilya, A Palmer - arXiv preprint arXiv:2410.00387, 2024 - arxiv.org
The data and compute requirements of current language modeling technology pose
challenges for the processing and analysis of low-resource languages. Declarative linguistic …
challenges for the processing and analysis of low-resource languages. Declarative linguistic …
Robust generalization strategies for morpheme glossing in an endangered language documentation context
Generalization is of particular importance in resource-constrained settings, where the
available training data may represent only a small fraction of the distribution of possible …
available training data may represent only a small fraction of the distribution of possible …
Bootstrapping UMR Annotations for Arapaho from Language Documentation Resources
Abstract Uniform Meaning Representation (UMR) is a semantic labeling system in the AMR
family designed to be uniformly applicable to typologically diverse languages. The UMR …
family designed to be uniformly applicable to typologically diverse languages. The UMR …
Wav2Gloss: Generating Interlinear Glossed Text from Speech
Thousands of the world's languages are in danger of extinction--a tremendous threat to
cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of …
cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of …
GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning
We introduce GrammaMT, a grammatically-aware prompting approach for machine
translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description …
translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description …