CIR at the NTCIR-17 ULTRE-2 Task
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910919617937408 |
|---|---|
| author | Yu, Lulu Bi, Keping Guo, Jiafeng Cheng, Xueqi |
| author_facet | Yu, Lulu Bi, Keping Guo, Jiafeng Cheng, Xueqi |
| contents | The Chinese academy of sciences Information Retrieval team (CIR) has participated in the NTCIR-17 ULTRE-2 task. This paper describes our approaches and reports our results on the ULTRE-2 task. We recognize the issue of false negatives in the Baidu search data in this competition is very severe, much more severe than position bias. Hence, we adopt the Dual Learning Algorithm (DLA) to address the position bias and use it as an auxiliary model to study how to alleviate the false negative issue. We approach the problem from two perspectives: 1) correcting the labels for non-clicked items by a relevance judgment model trained from DLA, and learn a new ranker that is initialized from DLA; 2) including random documents as true negatives and documents that have partial matching as hard negatives. Both methods can enhance the model performance and our best method has achieved nDCG@10 of 0.5355, which is 2.66% better than the best score from the organizer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_11852 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | CIR at the NTCIR-17 ULTRE-2 Task Yu, Lulu Bi, Keping Guo, Jiafeng Cheng, Xueqi Information Retrieval The Chinese academy of sciences Information Retrieval team (CIR) has participated in the NTCIR-17 ULTRE-2 task. This paper describes our approaches and reports our results on the ULTRE-2 task. We recognize the issue of false negatives in the Baidu search data in this competition is very severe, much more severe than position bias. Hence, we adopt the Dual Learning Algorithm (DLA) to address the position bias and use it as an auxiliary model to study how to alleviate the false negative issue. We approach the problem from two perspectives: 1) correcting the labels for non-clicked items by a relevance judgment model trained from DLA, and learn a new ranker that is initialized from DLA; 2) including random documents as true negatives and documents that have partial matching as hard negatives. Both methods can enhance the model performance and our best method has achieved nDCG@10 of 0.5355, which is 2.66% better than the best score from the organizer. |
| title | CIR at the NTCIR-17 ULTRE-2 Task |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2310.11852 |