IncDSI: Incrementally Updatable Document Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kishore, Varsha, Wan, Chao, Lovelace, Justin, Artzi, Yoav, Weinberger, Kilian Q.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916360015052800
author Kishore, Varsha
Wan, Chao
Lovelace, Justin
Artzi, Yoav
Weinberger, Kilian Q.
author_facet Kishore, Varsha
Wan, Chao
Lovelace, Justin
Artzi, Yoav
Weinberger, Kilian Q.
contents Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These models have achieved state-of-the-art performances for document retrieval across many benchmarks. These kinds of models have a significant limitation: it is not easy to add new documents after a model is trained. We propose IncDSI, a method to add documents in real time (about 20-50ms per document), without retraining the model on the entire dataset (or even parts thereof). Instead we formulate the addition of documents as a constrained optimization problem that makes minimal changes to the network parameters. Although orders of magnitude faster, our approach is competitive with re-training the model on the whole dataset and enables the development of document retrieval systems that can be updated with new information in real-time. Our code for IncDSI is available at https://github.com/varshakishore/IncDSI.
format Preprint
id arxiv_https___arxiv_org_abs_2307_10323
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle IncDSI: Incrementally Updatable Document Retrieval
Kishore, Varsha
Wan, Chao
Lovelace, Justin
Artzi, Yoav
Weinberger, Kilian Q.
Information Retrieval
Computation and Language
Machine Learning
Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These models have achieved state-of-the-art performances for document retrieval across many benchmarks. These kinds of models have a significant limitation: it is not easy to add new documents after a model is trained. We propose IncDSI, a method to add documents in real time (about 20-50ms per document), without retraining the model on the entire dataset (or even parts thereof). Instead we formulate the addition of documents as a constrained optimization problem that makes minimal changes to the network parameters. Although orders of magnitude faster, our approach is competitive with re-training the model on the whole dataset and enables the development of document retrieval systems that can be updated with new information in real-time. Our code for IncDSI is available at https://github.com/varshakishore/IncDSI.
title IncDSI: Incrementally Updatable Document Retrieval
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/2307.10323