paper-with-me

Papers

A Study on Token Pruning for ColBERT

2021-12-13 · Carlos Lassance, Maroua Maachou, Joohee Park, Stéphane Clinchant

The ColBERT model has recently been proposed as an effective BERT based ranker. By adopting a late interaction mechanism, a major advantage of ColBERT is that document representations can be precomputed in advance. However, the big downside of the model is the index size, which scales linearly with the number of tokens in the collection. In this paper, we study various designs for ColBERT models in order to attack this problem. While compression techniques have been explored to reduce the index size, in this paper we study token pruning techniques for ColBERT. We compare simple heuristics, as well as a single layer of attention mechanism to select the tokens to keep at indexing time. Our experiments show that ColBERT indexes can be pruned up to 30\% on the MS MARCO passage collection without a significant drop in performance. Finally, we experiment on MS MARCO documents, which reveal several challenges for such mechanism.

📄 PDF Abstract BibTeX arXiv:2112.06540

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Pruning 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Towards Lossless Token Pruning in Late-Interaction Retrieval Models

2025-04-17 · Yuxuan Zong, Benjamin Piwowarski

Late interaction neural IR models like ColBERT offer a competitive effectiveness-efficiency trade-off across many benchmarks. However, they require a huge memory space to store the contextual representation for all the d…

Retrieval

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models

2024-03-20 · Qi Liu, Gang Guo, Jiaxin Mao, Zhicheng Dou 외

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Dif…

Retrieval

ColBERT's [MASK]-based Query Augmentation: Effects of Quadrupling the Query Input Length

2024-08-24 · Ben Giacalone, Richard Zanibbi

A unique aspect of ColBERT is its use of [MASK] tokens in queries to score documents (query augmentation). Prior work shows [MASK] tokens weighting non-[MASK] query terms, emphasizing certain tokens over others , rather …

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

2026-06-04 · Eugene Yang, Andrew Yates, Dawn Lawrie, James Mayfield 외 arxiv

While ColBERT is an effective neural retrieval architecture, it requires a heavy index structure to support candidate set retrieval based on approximated token embeddings, gathering and decompressing document token embed…

FGR-ColBERT: Identifying Fine-Grained Relevance Tokens During Retrieval

2026-03-31 · Antonín Jarolím, Martin Fajčík arxiv

Document retrieval identifies relevant documents but does not provide fine-grained evidence cues, such as specific relevant spans. A possible solution is to apply an LLM after retrieval; however, this introduces signific…