Logo des Repositoriums
 

Blueprint for a Production-Ready Information Retrieval System based on Multi-Modal Embeddings

Kurzanzeige
dc.contributor.authorEbert, André
dc.contributor.authorApel, Anika
dc.contributor.authorChodyko, Piotr
dc.contributor.authorHiroyasu, Kyle
dc.contributor.authorIsmali, Festina
dc.contributor.authorKoo, Hyein
dc.contributor.authorKronburger, Julia
dc.contributor.authorPesch, Robert
dc.date.accessioned2021-12-14T10:57:58Z
dc.date.available2021-12-14T10:57:58Z
dc.date.issued2021
dc.description.abstractDeep Learning models for mapping documents from different domains, e.g., text, images, and audio, into a common vector space, enable a seamless information retrieval between the different domains and, thus, significantly improve the user experience of many expert tools. Despite various models for multi-modal mappings presented in scientific literature, the implementation and integration remain a challenge within the industry, especially for small or medium-sized companies. Reasons are, that developing such retrieval systems for production use-cases is a non-trivial task, requiring scalable, reliable, and cost-efficient infrastructure, services as well as adequate Deep Learning models. We present a generic and flexible blueprint architecture, targeting the development of a production-ready image-text retrieval search system using Kubernetes, MLflow, Elasticsearch, and integrating state-of-the-art Deep Learning models.en
dc.identifier.doi10.18420/informatik2021-095
dc.identifier.isbn978-3-88579-708-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/37765
dc.language.isoen
dc.publisherGesellschaft für Informatik, Bonn
dc.relation.ispartofINFORMATIK 2021
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-314
dc.subjectInformation Retrieval
dc.subjectImage-to-Text
dc.subjectMulti-Modal Embeddings
dc.subjectDeep Learning
dc.subjectArtificial Intelligence
dc.subjectData-Science to Production
dc.titleBlueprint for a Production-Ready Information Retrieval System based on Multi-Modal Embeddingsen
gi.citation.endPage1175
gi.citation.startPage1165
gi.conference.date27. September - 1. Oktober 2021
gi.conference.locationBerlin
gi.conference.sessiontitleWorkshop: Künstliche Intelligenz für kleine und mittlere Unternehmen (KI-KMU 2021)

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
N1-1.pdf
Größe:
349.3 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P314 - INFORMATIK 2021 - Computer Science & Sustainability