Papers by Arezoo Hatefi

1 papers
PromptStream: Self-Supervised News Story Discovery Using Topic-Aware Article Representations (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for news story discovery relied on sparse document representations such as keywords and TF-IDF vectors.
Approach: They propose a method that constructs article embeddings using cloze-style prompting and self-supervised contrastive learning techniques to tackle this task.
Outcome: The proposed model is able to identify coherent news stories within a news stream and to monitor their progress.

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