Flowchart images are converted to graphs by a fine-tuned vision model, then embedded as text chunks, letting a text-based retriever answer flowchart-related questions in telecom documents.
Lewis, Gady Agam, Shlomo Engelson Argamon, Ophir Frieder, David A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents
Flowchart images are converted to graphs by a fine-tuned vision model, then embedded as text chunks, letting a text-based retriever answer flowchart-related questions in telecom documents.