Papers with transfer strategies
TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing content-based recommendations fail when new users use them or a new article is created. |
| Approach: | They propose a model to transfer knowledge from a source corpus to a target corpus and use it to generate representations for unseen users in the future. |
| Outcome: | The proposed model can be used to generate representations for unseen users in the future. |
NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis (2022.lrec-1)
Copied to clipboard
Shamsuddeen Hassan Muhammad, David Ifeoluwa Adelani, Sebastian Ruder, Ibrahim Sa’id Ahmad, Idris Abdulmumin, Bello Shehu Bello, Monojit Choudhury, Chris Chinenye Emezue, Saheed Salahudeen Abdullahi, Anuoluwapo Aremu, Alípio Jorge, Pavel Brazdil
| Challenge: | Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. |
| Approach: | They propose a large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria. |
| Outcome: | The proposed dataset includes 30,000 tweets and a significant fraction of code-mixed tweets. |