Pulse 探索 nav.journalClub 辩论趋势研究者期刊

Join discussions, follow papers, and never miss your next session.

Download on theApp Store

首页探索 nav.journalClub 趋势

⌘+K

vitrivr-engine at the NTCIR-18 Lifelog-6 Task | Synapse

April 1, 20260 citationsOpen Access

View Full Paper

vitrivr-engine at the NTCIR-18 Lifelog-6 Task

LRLuca RossettoDublin City University

Key Points

The aim is to showcase how vitrivr contributes to the Lifelog Semantic Access subtask using an LLM-based approach.
Participation in the NTCIR Lifelog Semantic Access subtask
Utilization of LLM-based query transformation
Single-pass result generation without re-processing
Demonstrated efficiency in query handling
Improved semantic access capabilities
Results produced without additional refinement processes

Abstract

This paper discusses vitrivr's participation in the Lifelog Semantic Access subtask of the 6th edition of the NTCIR Lifelog. It is based on the system that participated in the 2024 Lifelog Search Challenge and only replaces the interactive query interface with an LLM-based query transformation method. All results are generated in one pass without any further re-processing or refinement.

问 AI

Like

Bookmark

Share

View Full Paper

Cite This Study

Luca Rossetto (Fri,) studied this question.

synapsesocial.com/papers/69cd7a1b5652765b073a703a https://doi.org/https://doi.org/10.20736/0002002047

问 AI

Like

Bookmark

Share

View Full Paper