Retrieval Augmented Spelling Correction for E-Commerce Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Xuan, Patki, Rohit, Everaert, Dante, Potts, Christopher
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916439976312832
author Guo, Xuan
Patki, Rohit
Everaert, Dante
Potts, Christopher
author_facet Guo, Xuan
Patki, Rohit
Everaert, Dante
Potts, Christopher
contents The rapid introduction of new brand names into everyday language poses a unique challenge for e-commerce spelling correction services, which must distinguish genuine misspellings from novel brand names that use unconventional spelling. We seek to address this challenge via Retrieval Augmented Generation (RAG). On this approach, product names are retrieved from a catalog and incorporated into the context used by a large language model (LLM) that has been fine-tuned to do contextual spelling correction. Through quantitative evaluation and qualitative error analyses, we find improvements in spelling correction utilizing the RAG framework beyond a stand-alone LLM. We also demonstrate the value of additional finetuning of the LLM to incorporate retrieved context.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11655
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Retrieval Augmented Spelling Correction for E-Commerce Applications
Guo, Xuan
Patki, Rohit
Everaert, Dante
Potts, Christopher
Computation and Language
Artificial Intelligence
The rapid introduction of new brand names into everyday language poses a unique challenge for e-commerce spelling correction services, which must distinguish genuine misspellings from novel brand names that use unconventional spelling. We seek to address this challenge via Retrieval Augmented Generation (RAG). On this approach, product names are retrieved from a catalog and incorporated into the context used by a large language model (LLM) that has been fine-tuned to do contextual spelling correction. Through quantitative evaluation and qualitative error analyses, we find improvements in spelling correction utilizing the RAG framework beyond a stand-alone LLM. We also demonstrate the value of additional finetuning of the LLM to incorporate retrieved context.
title Retrieval Augmented Spelling Correction for E-Commerce Applications
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.11655