Cross-encoder models, which jointly encode and score a query-item pair, ...
Dual encoder models are ubiquitous in modern classification and retrieva...
Recent years have seen a paradigm shift in NLP towards using pretrained
...
Efficient k-nearest neighbor search is a fundamental task, foundational ...
Ontonotes has served as the most important benchmark for coreference
res...
Opinion summarization is the task of creating summaries capturing popula...
We study algorithms for approximating pairwise similarity matrices that ...
Previous work has shown promising results in performing entity linking b...
Hierarchical clustering is a critical task in numerous domains. Many
app...
In many domains, relationships between categories are encoded in the
kno...
Bottom-up algorithms such as the classic hierarchical agglomerative
clus...
Due to large number of entities in biomedical knowledge bases, only a sm...
A case-based reasoning (CBR) system solves a new problem by retrieving
`...
Accurate parsing of citation reference strings is crucial to automatical...
Hierarchical clustering is a fundamental task often used to discover
mea...
We introduce Grinch, a new algorithm for large-scale, non-greedy hierarc...
String similarity models are vital for record linkage, entity resolution...
In supervised clustering, standard techniques for learning a pairwise
di...
Multimedia streaming services over spoken dialog systems have become
ubi...
Many modern clustering methods scale well to a large number of data item...