On Adaptive Knowledge Distillation with Generalized KL-Divergence Loss for Ranking Model Refinement-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

On Adaptive Knowledge Distillation with Generalized KL-Divergence Loss for Ranking Model Refinement

Published:2024-08-02 Issue: Volume:11 Page:81-90
ISSN:
Container-title:Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval
language:
Short-container-title:

Author:

Yang Yingrui¹^ORCID,He Shanxiu¹^ORCID,Yang Tao¹^ORCID

Affiliation:

1. Department of Computer Science, University of California, Santa Barbara, CA, USA

Funder

NSF

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3664190.3672522

Reference50 articles.

1. From ranknet to lambdarank to lambdamart: An overview;Burges Christopher JC;Learning,2010

2. Daniel Fernando Campos, Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, Li Deng, and Bhaskar Mitra. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. ArXiv, Vol. abs/1611.09268 (2016).

3. SimLM Checkpoint. [n. d.]. https://huggingface.co/intfloat/simlm-base-msmarco-finetuned. ( [n. d.]).

4. Co-Condenser. 2021. https://huggingface.co/Luyu/co-condenser-marco. (2021).

5. Gordon V. Cormack, Charles L. A. Clarke, and Stefan Büttcher. 2009. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. SIGIR (2009).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP