paper-with-me

홈 › Papers

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval

2022-07-06 · Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training. We use a replaced language modeling objective, which is inspired by ELECTRA, to improve the sample efficiency and reduce the mismatch of the input distribution between pre-training and fine-tuning. SimLM only requires access to unlabeled corpus, and is more broadly applicable when there are no labeled data or queries. We conduct experiments on several large-scale passage retrieval datasets, and show substantial improvements over strong baselines under various settings. Remarkably, SimLM even outperforms multi-vector approaches such as ColBERTv2 which incurs significantly more storage cost. Our code and model check points are available at https://github.com/microsoft/unilm/tree/master/simlm .

📄 PDF Abstract BibTeX arXiv:2207.02578

Code (1)

microsoft/unilm 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingPassage RetrievalRetrieval

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
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…

Similar Papers 제목 키워드 기반

CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval

2023-04-05 · Xing Wu, Guangyuan Ma, Peng Wang, Meng Lin 외

Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to …

Passage RetrievalRetrievalSentence

MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers

2022-12-15 · Kun Zhou, Xiao Liu, Yeyun Gong, Wayne Xin Zhao 외

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the q…

DecoderPassage RetrievalRetrieval

Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval

2023-08-16 · Guangyuan Ma, Xing Wu, Peng Wang, Zijia Lin 외

In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage the capabilities of LLMs for document expa…

Contrastive LearningLanguage ModelingLanguage ModellingLarge Language Model+2

A Gradient Accumulation Method for Dense Retriever under Memory Constraint

2024-06-18 · Jaehee Kim, Yukyung Lee, Pilsung Kang

InfoNCE loss is commonly used to train dense retriever in information retrieval tasks. It is well known that a large batch is essential to stable and effective training with InfoNCE loss, which requires significant hardw…

Information RetrievalRetrieval

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

2022-08-16 · Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin 외

Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i.e., vectors) of the query and the passages. Recent studies have explored improving pre-train…

DecoderPassage RetrievalRetrievalSentence