Papers by Annika Simonsen

2 papers
Good or Bad News? Exploring GPT-4 for Sentiment Analysis for Faroese on a Public News Corpora (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on sentiment analysis in low-resource languages have focused on major languages and emotionally laden text genres like social media and reviews.
Approach: They propose to use GPT-4 for sentiment analysis on Faroese news texts using a multi-class approach with 225 sentences analysed in 170 articles.
Outcome: The proposed model performs remarkably well on 225 sentences and 170 articles compared to human annotators .
Creating a Basic Language Resource Kit for Faroese (2022.lrec-1)

Copied to clipboard

Challenge: a few resources exist for Faroese, but many of them are insufficient size and quality or are not easily accessible.
Approach: They propose to make a BLARK for Faroese that will be open-source and use other languages' resources.
Outcome: The proposed BLARK will be a pillar in Faroese LR, and will be open-source . authors comment on the faulty yet sprouting LT situation in the Faroest islands .

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