Results 51 to 60 of about 372,511 (339)
Distributed Ranking Methods for Geographic Information Retrieval [PDF]
, 2005 Geographic Information Retrieval is concerned with retrieving documents that are related to some location. This paper addresses the ranking of documents by both textual and spatial relevance. To this end, we introduce distributed ranking, where similar documents are ranked spread in the list instead of consecutively.
Marc van Kreveld +3 more
openaire +5 more sources
Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 Large Language Models (LLMs) have demonstrated remarkable zero-shot generalization across various language-related tasks, including search engines. However, existing work utilizes the generative ability of LLMs for Information Retrieval (IR) rather than ...
Weiwei Sun +5 more
semanticscholar +1 more source
Information Retrieval in an Infodemic: The Case of COVID-19 Publications
Journal of Medical Internet Research, 2021 BackgroundThe COVID-19 global health crisis has led to an exponential surge in published scientific literature. In an attempt to tackle the pandemic, extremely large COVID-19–related corpora are being created, sometimes with ...
Douglas Teodoro +8 more
doaj +1 more source
Neural ranking models for document retrieval [PDF]
Information Retrieval Journal, 2021 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 hand-crafted features. Recently, researchers have leveraged deep learning models in
M. Trabelsi +3 more
semanticscholar +1 more source
In-Context Retrieval-Augmented Language Models [PDF]
Transactions of the Association for Computational Linguistics, 2023 Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can mitigate
Ori Ram +6 more
semanticscholar +1 more source
Learning to Truncate Ranked Lists for Information Retrieval
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 Ranked list truncation is of critical importance in a variety of professional information retrieval applications such as patent search or legal search. The goal is to dynamically determine the number of returned documents according to some user-defined objectives, in order to reach a balance between the overall utility of the results and user efforts ...
Wu, Chen +5 more
openaire +2 more sources
Text-to-Image GAN-Based Scene Retrieval and Re-Ranking Considering Word Importance
IEEE Access, 2019 In this paper, we propose a novel scene retrieval and re-ranking method based on a text-to-image Generative Adversarial Network (GAN). The proposed method generates an image from an input query sentence based on the text-to-image GAN and then retrieves a
Rintaro Yanagi +3 more
doaj +1 more source
Graph-Embedding Empowered Entity Retrieval
, 2020 In this research, we improve upon the current state of the art in entity retrieval by re-ranking the result list using graph embeddings. The paper shows that graph embeddings are useful for entity-oriented search tasks.
D Metzler +7 more
core +1 more source
A probabilistic justification for using tf.idf term weighting in information retrieval [PDF]
, 2000 This paper presents a new probabilistic model of information retrieval. The most important modeling assumption made is that documents and queries are defined by an ordered sequence of single terms.
Hiemstra, D.
core +2 more sources
Sensors, 2020 Billions of electric equipment are connected to Internet of Things (IoT)-based sensor networks, where they continuously generate a large volume of status information of assets. So, there is a need for state-aware information retrieval technology that can
Haesung Lee, Byungsung Lee
doaj +1 more source