paper-with-me

홈 › Papers

Understanding BERT Rankers Under Distillation

2020-07-21 · Luyu Gao, Zhuyun Dai, Jamie Callan

Deep language models such as BERT pre-trained on large corpus have given a huge performance boost to the state-of-the-art information retrieval ranking systems. Knowledge embedded in such models allows them to pick up complex matching signals between passages and queries. However, the high computation cost during inference limits their deployment in real-world search scenarios. In this paper, we study if and how the knowledge for search within BERT can be transferred to a smaller ranker through distillation. Our experiments demonstrate that it is crucial to use a proper distillation procedure, which produces up to nine times speedup while preserving the state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2007.11088

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalRetrieval

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Multi-Head Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation

2021-03-11 · Jaekeol Choi, Euna Jung, Jangwon Suh, Wonjong Rhee

BERT-based Neural Ranking Models (NRMs) can be classified according to how the query and document are encoded through BERT's self-attention layers - bi-encoder versus cross-encoder. Bi-encoder models are highly efficient…

Document Ranking

How Different are Pre-trained Transformers for Text Ranking?

2022-04-05 · David Rau, Jaap Kamps

In recent years, large pre-trained transformers have led to substantial gains in performance over traditional retrieval models and feedback approaches. However, these results are primarily based on the MS Marco/TREC Deep…

Passage RetrievalRetrieval

Distillation versus Contrastive Learning: How to Train Your Rerankers

2025-07-11 · Zhichao Xu, Zhiqi Huang, Shengyao Zhuang, Vivek Srikumar arxiv

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge…

Knowledge DistillationInformation RetrievalContrastive Learning

On the Calibration and Uncertainty of Neural Learning to Rank Models

2021-01-12 · Gustavo Penha, Claudia Hauff

According to the Probability Ranking Principle (PRP), ranking documents in decreasing order of their probability of relevance leads to an optimal document ranking for ad-hoc retrieval. The PRP holds when two conditions a…

Document RankingLearning-To-RankRetrieval

TabRank: Chain-of-Thought Distillation for Table Re-Rankers

2026-07-28 · Adarsh Singh, Kushal Raj Bhandari, Jianxi Gao, Soham Dan 외 arxiv

The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely heavily on rerankers to refine candidate lists produced by efficient …

Information RetrievalNatural QuestionsPassage RetrievalTable Retrieval