What question did this study set out to answer?

Evaluate the effectiveness of various methods in information retrieval tasks.

April 1, 2026Open Access

THUIR at the NTCIR-16 WWW-4 Task

Key Points

Evaluate the effectiveness of various methods in information retrieval tasks.
Participated in the English subtask of NTCIR-16 WWW-4.
Adopted learning-to-rank models for ranking web content.
Utilized a pre-trained language model specifically tailored for information retrieval.
Employed BERT with prompt learning to enhance retrieval performance.
Demonstrated the importance of task-specific pre-training for information retrieval.
Indicated that a simplistic prompt method did not significantly improve ranking performance.

Abstract

The THUIR team participates in the English subtask of the NTCIR-16 We Want Web with CENTRE(WWW-4) task. This paper elaborates on our methods and discusses the experimental results. We adopt three methods, namely learning-to-rank models, a pre-trained language model tailored for information retrieval, and BERT with prompt learning. Experimental results demonstrate the importance of designing pre-training task specifically for information retrieval. Results also suggest the relatively simple prompt method cannot effectively improve the ranking performance.

Perguntar à IA

Bookmark

View Full Paper

Cite This Study

Yang et al. (Tue,) studied this question.

synapsesocial.com/papers/69cd7a1b5652765b073a6edf https://doi.org/https://doi.org/10.20736/0002002290

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Perguntar à IA

Bookmark

View Full Paper