DAG: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered Uralic Languages using ChatGPT

2024/11/03 by Mika Hämäläinen, Hämäläinen, Mika · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2411.01531

openalex publication_date 2024/11/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

We showcase that ChatGPT can be used to disambiguate lemmas in two endangered languages ChatGPT is not proficient in, namely Erzya and Skolt Sami. We augment our prompt by providing dictionary translations of the candidate lemmas to a majority language - Finnish in our case. This dictionary augmented generation approach results in 50% accuracy for Skolt Sami and 41% accuracy for Erzya. On a closer inspection, many of the error types were of the kind even an untrained human annotator would make.

Cited by

• Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data

Related

• Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model
• Ve'rdd. Narrowing the Gap between Paper Dictionaries, Low-Resource NLP\n and Community Involvement
• Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability
• Leveraging Transformer-Based Models for Predicting Inflection Classes of Words in an Endangered Sami Language
• Part of speech and gramset tagging algorithms for unknown words based on\n morphological dictionaries of the Veps and Karelian languages