What question did this study set out to answer?

This research aims to enhance dense vector search performance in specific subtasks of NTCIR-17.

April 1, 2026Open Access

KANDUH at the NTCIR-17 Transfer Task

Key Points

This research aims to enhance dense vector search performance in specific subtasks of NTCIR-17.
Participated in Transfer subtasks 1 and 2 of NTCIR-17.
Utilized BM25 for document filtering.
Applied dense vector retrieval techniques.
Highest nDCG@20 achieved was 0.4339 using finetuned DeBERTa-v2 with MSMARCO and NTCIR-1 data.
Lowest nDCG@20 recorded was 0.0751 with only MSMARCO data finetuning.

Abstract

The KANDUH team participated in the Transfer subtasks 1 and 2 of NTCIR-17.In this paper, we report on our approach to solving the problem and the results.Subtasks 1 and 2 address the dense vector search task, respectively.In both subtasks 1 and 2, we used BM25 to filter documents, followed by dense vector retrieval.The method with the highest nDCG@20 was 0.4339 the one that first finetuned DeBERTa-v2 with MSMARCO and then additionally finetuned with NTCIR-1 data.On the other hand, the method with the lowest nDCG@20 was 0.0751 the one that fine-tuned only MSMARCO data.

AI से पूछें

Bookmark

View Full Paper