What question did this study set out to answer?

The aim is to improve the linking of minutes to budget data using classification techniques on table cells.

April 1, 2026Open Access

fuys Team at the NTCIR-17 QA Lab-PoliInfo-4 Task

Key Points

The aim is to improve the linking of minutes to budget data using classification techniques on table cells.
Used binary classification to identify relevant tables based on their cells.
Encoded and combined text from tags and table cells for analysis.
Explored different methods of joining table cell text to assess relevance accuracy.
Achieved best accuracy when text in table cells was joined column by column.
Table relevance was determined by the presence of related words in the cells.

Abstract

This paper reports on the fuys team's NTCIR-17 QA Lab-PoliInfo-4 Minutes-to-Budget Linking (MBLink) results. We thought that related tables could be found by focusing on the cells of the table. Learning inferences were made by combining the text of tag with an ID and the text of table cell. The two were encoded and combined to perform a binary classification. We considered a table relevant if there was at least one related word in the table's cells. We also tried this when the text of a table cell was joined column by column and combined with the text of a tag with an ID. The best accuracy was obtained when the text in table cells was joined column by column.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper