paper-with-me

Papers

Retrieval Augmented Spelling Correction for E-Commerce Applications

2024-10-15 · Xuan Guo, Rohit Patki, Dante Everaert, Christopher Potts

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.

📄 PDF Abstract BibTeX arXiv:2410.11655

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelRAGRetrievalRetrieval-augmented GenerationSpelling Correction

Methods 이 논문이 사용한 방법론

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 &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
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…
WordPiece 설명 없음
Residual Connection 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…

Similar Papers 제목 키워드 기반

Spelling Correction using Phonetics in E-commerce Search

2022-05-01 · ECNLP (ACL) 2022 5 · Fan Yang, Alireza Bagheri Garakani, Yifei Teng, Yan Gao 외

In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries. However, resolving phonetic errors is a critical but much overlooked area.…

Spelling Correction

RSpell: Retrieval-augmented Framework for Domain Adaptive Chinese Spelling Check

2023-08-16 · Siqi Song, Qi Lv, Lei Geng, Ziqiang Cao 외

Chinese Spelling Check (CSC) refers to the detection and correction of spelling errors in Chinese texts. In practical application scenarios, it is important to make CSC models have the ability to correct errors across di…

Retrieval

English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics

2022-06-01 · LREC 2022 6 · Kyle Goslin, Markus Hofmann

Spelling correction utilities have become commonplace during the writing process, however, many spelling correction utilities suffer due to the size and quality of dictionaries available to aid correction. Many terms, ac…

Information RetrievalRetrievalSpelling Correction

Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluation

2026-02-25 · Saurabh K Singh arxiv

Healthcare question-answering (QA) systems face a persistent challenge: users submit queries with spelling errors at rates substantially higher than those found in the professional documents they search. This paper prese…

Context-Sensitive Malicious Spelling Error Correction

2019-01-23 · Hongyu Gong, Yuchen Li, Suma Bhat, Pramod Viswanath

Misspelled words of the malicious kind work by changing specific keywords and are intended to thwart existing automated applications for cyber-environment control such as harassing content detection on the Internet and e…

Spam detectionSpelling CorrectionWord Embeddings