paper-with-me

홈 › Papers

Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders

2023-03-31 · Daniel Campos, Alessandro Magnani, ChengXiang Zhai

In this paper, we consider the problem of improving the inference latency of language model-based dense retrieval systems by introducing structural compression and model size asymmetry between the context and query encoders. First, we investigate the impact of pre and post-training compression on the MSMARCO, Natural Questions, TriviaQA, SQUAD, and SCIFACT, finding that asymmetry in the dual encoders in dense retrieval can lead to improved inference efficiency. Knowing this, we introduce Kullback Leibler Alignment of Embeddings (KALE), an efficient and accurate method for increasing the inference efficiency of dense retrieval methods by pruning and aligning the query encoder after training. Specifically, KALE extends traditional Knowledge Distillation after bi-encoder training, allowing for effective query encoder compression without full retraining or index generation. Using KALE and asymmetric training, we can generate models which exceed the performance of DistilBERT despite having 3x faster inference.

📄 PDF Abstract BibTeX arXiv:2304.01016

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationLanguage ModelingLanguage ModellingNatural QuestionsRetrievalTriviaQA

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Pruning 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…
Multi-Head Attention 설명 없음
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.
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…
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…

Similar Papers 제목 키워드 기반

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

2024-11-12 · Anas Awadalla, Le Xue, Manli Shu, An Yan 외

We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale a…

DescriptiveImage Captioning

Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection

2021-09-22 · Negar Arabzadeh, Xinyi Yan, Charles L. A. Clarke

Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as…

GPUInformation RetrievalRetrieval

A Study on the Efficiency and Generalization of Light Hybrid Retrievers

2022-10-04 · Man Luo, Shashank Jain, Anchit Gupta, Arash Einolghozati 외

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybri…

Adversarial AttackContrastive LearningKnowledge Distillation

To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers

2022-04-30 · Hang Li, Shuai Wang, Shengyao Zhuang, Ahmed Mourad 외

Current pre-trained language model approaches to information retrieval can be broadly divided into two categories: sparse retrievers (to which belong also non-neural approaches such as bag-of-words methods, e.g., BM25) a…

Information RetrievalLanguage ModellingRetrieval

Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling

2024-03-06 · Chao-Wei Huang, Chen-An Li, Tsu-Yuan Hsu, Chen-Yu Hsu 외

Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages. However, dense retrievers typically require a substantial …

Information RetrievalRetrieval