4 accepted papers
Document summarization helps readers focus on the "content-of-interest", a *subjective* and *time-variant* quantity. Capturing this *dynamic subjectivity* requires modeling how user preferences evolve over time, thereby demanding *personalized summarization*. Recent news recommendation and summariza…
Real-world knowledge is often organized as hierarchies such as product taxonomies, medical ontologies, and label trees, yet learning hierarchical representations is challenging due to asymmetric structure and noisy semantics. We introduce Polaris, a polar hyperspherical embedding framework that sepa…
Reviewer Matchmaking (RM) is a pivotal process in academic publishing that aligns manuscripts with appropriate reviewers based on their expertise and prior publications. The demand for an automated RM system has escalated with the significant surge in submissions over the past decade. State-of-the-a…
Text summarization models are evaluated in terms of their accuracy and quality using various measures such as ROUGE, BLEU, METEOR, BERTScore, PYRAMID, readability, and several other recently proposed ones. The central objective of all accuracy measures is to evaluate the model's ability to capture $…