lecs lab
@lecslab.bsky.social
The Low-resource + Endangered language and Computational Semantics (LECS) group at @bouldernlp.bsky.social, led by @alexispalmer.bsky.social
Bibles are the only large parallel corpora for many languages—so how can we design MT systems that work well in other domains?
“From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation” by Ali Marashian, @covetedfish.bsky.social, @alexispalmer.bsky.social, and others
“From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation” by Ali Marashian, @covetedfish.bsky.social, @alexispalmer.bsky.social, and others
December 3, 2024 at 4:27 PM
Bibles are the only large parallel corpora for many languages—so how can we design MT systems that work well in other domains?
“From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation” by Ali Marashian, @covetedfish.bsky.social, @alexispalmer.bsky.social, and others
“From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation” by Ali Marashian, @covetedfish.bsky.social, @alexispalmer.bsky.social, and others
Can RAG+LLM systems help boost small models for rare languages?
Find out in “Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation” by Bhargav Shandilya and @alexispalmer.bsky.social
arxiv.org/abs/2410.00387
Find out in “Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation” by Bhargav Shandilya and @alexispalmer.bsky.social
arxiv.org/abs/2410.00387
Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation
The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential ...
arxiv.org
December 2, 2024 at 6:43 PM
Can RAG+LLM systems help boost small models for rare languages?
Find out in “Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation” by Bhargav Shandilya and @alexispalmer.bsky.social
arxiv.org/abs/2410.00387
Find out in “Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation” by Bhargav Shandilya and @alexispalmer.bsky.social
arxiv.org/abs/2410.00387
Reposted by lecs lab
Reposted by lecs lab
📅 Tues. 2-3:30, Poster Session 3
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
November 8, 2024 at 6:40 PM
📅 Tues. 2-3:30, Poster Session 3
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
🗺️GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text [EMNLP Main]
Hi, we just made an account for the LECS Lab at CU Boulder, and we'd love to be included!
November 12, 2024 at 11:37 PM
Hi, we just made an account for the LECS Lab at CU Boulder, and we'd love to be included!
Hi, we just made an account for the LECS Lab at CU Boulder (led by @alexispalmer.bsky.social)!
November 12, 2024 at 11:36 PM
Hi, we just made an account for the LECS Lab at CU Boulder (led by @alexispalmer.bsky.social)!