Dynamicretriever: A pre-training model-based IR system with neither sparse nor dense index
Web search provides a promising way for people to obtain information and has been
extensively studied. With the surgence of deep learning and large-scale pre-training …
extensively studied. With the surgence of deep learning and large-scale pre-training …
Lagrangian inference for ranking problems
We propose a novel combinatorial inference framework to conduct general uncertainty
quantification in ranking problems. We consider the widely adopted Bradley-Terry-Luce …
quantification in ranking problems. We consider the widely adopted Bradley-Terry-Luce …
Selective weak supervision for neural information retrieval
This paper democratizes neural information retrieval to scenarios where large scale
relevance training signals are not available. We revisit the classic IR intuition that anchor …
relevance training signals are not available. We revisit the classic IR intuition that anchor …
I3 retriever: incorporating implicit interaction in pre-trained language models for passage retrieval
Passage retrieval is a fundamental task in many information systems, such as web search
and question answering, where both efficiency and effectiveness are critical concerns. In …
and question answering, where both efficiency and effectiveness are critical concerns. In …
DynamicRetriever: a pre-trained model-based IR system without an explicit index
Web search provides a promising way for people to obtain information and has been
extensively studied. With the surge of deep learning and large-scale pre-training techniques …
extensively studied. With the surge of deep learning and large-scale pre-training techniques …
Computational understanding of narratives: A survey
Storytelling, and the delivery of societal narratives, enable human beings to communicate,
connect, and understand one another and the world around them. Narratives can be defined …
connect, and understand one another and the world around them. Narratives can be defined …
Neural ranking models for document retrieval
Ranking models are the main components of information retrieval systems. Several
approaches to ranking are based on traditional machine learning algorithms using a set of …
approaches to ranking are based on traditional machine learning algorithms using a set of …
IART: Intent-aware response ranking with transformers in information-seeking conversation systems
Personal assistant systems, such as Apple Siri, Google Assistant, Amazon Alexa, and
Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as …
Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as …
Hard negatives or false negatives: Correcting pooling bias in training neural ranking models
Neural ranking models (NRMs) have become one of the most important techniques in
information retrieval (IR). Due to the limitation of relevance labels, the training of NRMs …
information retrieval (IR). Due to the limitation of relevance labels, the training of NRMs …
Efficient self-supervised metric information retrieval: a bibliography based method applied to COVID literature
G Moro, L Valgimigli - Sensors, 2021 - mdpi.com
The literature on coronaviruses counts more than 300,000 publications. Finding relevant
papers concerning arbitrary queries is essential to discovery helpful knowledge. Current …
papers concerning arbitrary queries is essential to discovery helpful knowledge. Current …