paper-with-me

홈 › Papers

Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages?

2025-02-13 · Shira Wein

While ChatGPT and GPT-based models are able to effectively perform many tasks without additional fine-tuning, they struggle with related to extremely low-resource languages and indigenous languages. Uniform Meaning Representation (UMR), a semantic representation designed to capture the meaning of texts in many languages, is well-poised to be leveraged in the development of low-resource language technologies. In this work, we explore the downstream technical utility of UMR for low-resource languages by incorporating it into GPT-4 prompts. Specifically, we examine the ability of GPT-4 to perform translation from three indigenous languages (Navajo, Ar\'apaho, and Kukama), with and without demonstrations, as well as with and without UMR annotations. Ultimately we find that in the majority of our test cases, integrating UMR into the prompt results in a statistically significant increase in performance, which is a promising indication of future applications of the UMR formalism.

📄 PDF Abstract BibTeX arXiv:2502.08900

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Theoretical and Practical Issues in the Semantic Annotation of Four Indigenous Languages

2021-11-01 · EMNLP (LAW, DMR) 2021 11 · Jens E. L. Van Gysel, Meagan Vigus, Lukas Denk, Andrew Cowell 외

Computational resources such as semantically annotated corpora can play an important role in enabling speakers of indigenous minority languages to participate in government, education, and other domains of public life in…

IndT5: A Text-to-Text Transformer for 10 Indigenous Languages

2021-04-04 · NAACL (AmericasNLP) 2021 6 · El Moatez Billah Nagoudi, Wei-Rui Chen, Muhammad Abdul-Mageed, Hasan Cavusogl

Transformer language models have become fundamental components of natural language processing based pipelines. Although several Transformer models have been introduced to serve many languages, there is a shortage of mode…

Language ModelingLanguage ModellingMachine TranslationTranslation

Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learning

2022-05-14 · Wei-Rui Chen, Muhammad Abdul-Mageed

Machine translation (MT) involving Indigenous languages, including those possibly endangered, is challenging due to lack of sufficient parallel data. We describe an approach exploiting bilingual and multilingual pretrain…

Data AugmentationMachine TranslationTransfer LearningTranslation

Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas

2021-06-01 · NAACL (AmericasNLP) 2021 6 · Manuel Mager, Arturo Oncevay, Abteen Ebrahimi, John Ortega 외

This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas. The shared task featured two independent tracks, and participants submitted machine translatio…

Machine TranslationTranslation

NLP Progress in Indigenous Latin American Languages

2024-04-08 · Atnafu Lambebo Tonja, Fazlourrahman Balouchzahi, Sabur Butt, Olga Kolesnikova 외

The paper focuses on the marginalization of indigenous language communities in the face of rapid technological advancements. We highlight the cultural richness of these languages and the risk they face of being overlooke…