Papers by Daniel Whitenack

3 papers
Phone-ing it in: Towards Flexible Multi-Modal Language Model Training by Phonetic Representations of Data (2022.acl-long)

Copied to clipboard

Challenge: Pre-trained language models are increasingly applied in ways that are agnostic to targeted downstream tasks.
Approach: They propose a multi-modal approach to train language models using whatever text and/or audio data might be available in a language.
Outcome: The proposed approach improves on pre-trained models on Swahili and Kinyarwanda data, with an improvement of up to 6% over models that are trained from scratch.
Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks (2022.emnlp-main)

Copied to clipboard

Challenge: In total, the initial release of the Bloom Library datasets covers 363 languages across 32 language families.
Approach: They present a set of multimodal and multilingual datasets for language modeling, image captioning, visual storytelling, and speech synthesis/recognition.
Outcome: The Bloom Library datasets cover 363 languages across 32 language families.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations