paper-with-me

홈 › Papers

Transformer Memory as a Differentiable Search Index

2022-02-14 · Yi Tay, Vinh Q. Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta, Tal Schuster, William W. Cohen, Donald Metzler

In this paper, we demonstrate that information retrieval can be accomplished with a single Transformer, in which all information about the corpus is encoded in the parameters of the model. To this end, we introduce the Differentiable Search Index (DSI), a new paradigm that learns a text-to-text model that maps string queries directly to relevant docids; in other words, a DSI model answers queries directly using only its parameters, dramatically simplifying the whole retrieval process. We study variations in how documents and their identifiers are represented, variations in training procedures, and the interplay between models and corpus sizes. Experiments demonstrate that given appropriate design choices, DSI significantly outperforms strong baselines such as dual encoder models. Moreover, DSI demonstrates strong generalization capabilities, outperforming a BM25 baseline in a zero-shot setup.

📄 PDF Abstract BibTeX arXiv:2202.06991

Code (1)

ArvinZhuang/DSI-transformers pytorch

Tasks

Information RetrievalRetrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Memory-Efficient Differentiable Transformer Architecture Search

2021-05-31 · Findings (ACL) 2021 8 · Yuekai Zhao, Li Dong, Yelong Shen, Zhihua Zhang 외

Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the search process infeasible. To this end, we pr…

DSI++: Updating Transformer Memory with New Documents

2022-12-19 · Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani 외

Differentiable Search Indices (DSIs) encode a corpus of documents in model parameters and use the same model to answer user queries directly. Despite the strong performance of DSI models, deploying them in situations whe…

Continual LearningNatural QuestionsRetrieval

Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation

2022-06-21 · Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei 외

The Differentiable Search Index (DSI) is an emerging paradigm for information retrieval. Unlike traditional retrieval architectures where index and retrieval are two different and separate components, DSI uses a single t…

Information RetrievalPassage RetrievalRetrieval

Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor Search

2023-11-30 · Qiang Yue, Xiaoliang Xu, Yuxiang Wang, Yikun Tao 외

Given a vector dataset $\mathcal{X}$, a query vector $\vec{x}_q$, graph-based Approximate Nearest Neighbor Search (ANNS) aims to build a proximity graph (PG) as an index of $\mathcal{X}$ and approximately return vectors …

Quantization

Transformers are Stateless Differentiable Neural Computers

2026-02-27 · Bo Tang, Weiwei Xie arxiv

Differentiable Neural Computers (DNCs) were introduced as recurrent architectures equipped with an addressable external memory supporting differentiable read and write operations. Transformers, in contrast, are nominally…