What question did this study set out to answer?

This research aims to improve cell type classification and retrieval methods for the UFO task at NTCIR-17.

April 1, 2026Open Access

KSU at the NTCIR-17 UFO Task

Key Points

This research aims to improve cell type classification and retrieval methods for the UFO task at NTCIR-17.
Developed exhaustively tree structures for cell type classification in the TDE subtask.
Implemented cell retrieval methods based on cell classification in the TTRE subtask.
Evaluated performance using F-measure scores in formal and late submission runs.
Achieved a 95.37% F-measure score for ID81 in the TDE subtask.
For TTRE, the F-measure scores were 9.18%, 4.08%, and 6.63% for ID99 on Name, Value, and Total, respectively.
In late submission runs for TTRE, achieved scores of 32.21%, 27.19%, and 29.70% for ID127 on Name, Value, and Total, respectively.

Abstract

This paper describes the methods and results of Team KSU for the UFO task at NTCIR-17. In the TDE subtask, we designed methods for cell type classification using exhaustive tree structures based on the spanning sizes of the merged cells in the table. In the TTRE subtask, we designed methods for cell retrieval based on the cell class. Scores on the F-measure in the formal run were 95.37% for ID81 in TDE and 9.18%, 4.08%, and 6.63% for ID99 on the Name, Value, and Total, respectively, in TTRE. Scores on the F-measure including the formal run and late submission run were 95.37% for ID81 in TDE and 32.21%, 27.19%, and 29.70% for ID127 on the Name, Value, and Total, respectively, in TTRE.

Read Full Paperexternally

AI से पूछें

Bookmark

View Full Paper