Knowledge graphs: An information retrieval perspective
In this survey, we provide an overview of the literature on knowledge graphs (KGs) in the
context of information retrieval (IR). Modern IR systems can benefit from information …
context of information retrieval (IR). Modern IR systems can benefit from information …
Corpusbrain++: A continual generative pre-training framework for knowledge-intensive language tasks
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents
from trustworthy corpora, eg, Wikipedia, to produce specific answers. Very recently, a pre …
from trustworthy corpora, eg, Wikipedia, to produce specific answers. Very recently, a pre …
Novel entity discovery from web tables
When working with any sort of knowledge base (KB) one has to make sure it is as complete
and also as up-to-date as possible. Both tasks are non-trivial as they require recall-oriented …
and also as up-to-date as possible. Both tasks are non-trivial as they require recall-oriented …
Robust neural information retrieval: An adversarial and out-of-distribution perspective
Recent advances in neural information retrieval (IR) models have significantly enhanced
their effectiveness over various IR tasks. The robustness of these models, essential for …
their effectiveness over various IR tasks. The robustness of these models, essential for …
Analyzing history-related posts in twitter
Y Sumikawa, A Jatowt - International Journal on Digital Libraries, 2021 - Springer
Microblogging platforms such as Twitter have been increasingly used nowadays to share
information between users. They are also convenient means for propagating content related …
information between users. They are also convenient means for propagating content related …
Synthetic query generation using large language models for virtual assistants
Virtual Assistants (VAs) are important Information Retrieval platforms that help users
accomplish various tasks through spoken commands. The speech recognition system …
accomplish various tasks through spoken commands. The speech recognition system …
Wikipedia graph mining: dynamic structure of collective memory
Wikipedia is the biggest encyclopedia ever created and the fifth most visited website in the
world. Tens of millions of people surf it every day, seeking answers to various questions …
world. Tens of millions of people surf it every day, seeking answers to various questions …
Sleeping beauties in meme diffusion
L Zhang, K Xu, J Zhao - Scientometrics, 2017 - Springer
A sleeping beauty in diffusion indicates that certain information, whether an idea or
innovation, will experience a hibernation period before it undergoes a sudden spike of …
innovation, will experience a hibernation period before it undergoes a sudden spike of …
Generating categories for sets of entities
Category systems are central components of knowledge bases, as they provide a
hierarchical grouping of semantically related concepts and entities. They are a unique and …
hierarchical grouping of semantically related concepts and entities. They are a unique and …
Early discovery of emerging entities in microblogs
Keeping up to date on emerging entities that appear every day is indispensable for various
applications, such as social-trend analysis and marketing research. Previous studies have …
applications, such as social-trend analysis and marketing research. Previous studies have …