What question did this study set out to answer?

This research aims to classify budget arguments within political information effectively.

April 1, 2026Open Access

OUC at the NTCIR-16 QA Lab-PoliInfo-3 Budget Argument Mining

Key Points

This research aims to classify budget arguments within political information effectively.
Participated in the Budget Argument Mining subtask of NTCIR-16 QA Lab-PoliInfo-3.
Utilized a fine-tuned BERT classifier for argument classification.
Employed TF-IDF vectorization and cosine similarity to link related documents.
Achieved the second highest score of 0.5716 in argument classification among all participants.
Attained the highest score of 0.6596 in linking related IDs using the cosine similarity method.

Abstract

The OUC team participated in the Budget Argument Mining subtask of NTCIR-16 Question Answering Lab for Political Information 3 (QA Lab-PoliInfo-3). In this paper, we report on our methods for this task and discuss the results. We performed argument classification using a fine-tuned BERT classifier. This method showed the second highest score (0.5716) among the participants in the test data. We also performed linking relatedID using TF-IDF vectorization of documents and calculation of their cosine similarity. This method showed the highest score (0.6596) among the participants in the test data.

Read Full Paperexternally

AI से पूछें

Bookmark

View Full Paper