EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Li, Wang, Qifan, Chi, Jianfeng, Liu, Jiahao, Wang, Jingang, Feng, Fuli, Xu, Zenglin, Fang, Yi, Huang, Lifu, Liu, Dongfang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913385095888896
author Yang, Li
Wang, Qifan
Chi, Jianfeng
Liu, Jiahao
Wang, Jingang
Feng, Fuli
Xu, Zenglin
Fang, Yi
Huang, Lifu
Liu, Dongfang
author_facet Yang, Li
Wang, Qifan
Chi, Jianfeng
Liu, Jiahao
Wang, Jingang
Feng, Fuli
Xu, Zenglin
Fang, Yi
Huang, Lifu
Liu, Dongfang
contents Product attribute value extraction involves identifying the specific values associated with various attributes from a product profile. While existing methods often prioritize the development of effective models to improve extraction performance, there has been limited emphasis on extraction efficiency. However, in real-world scenarios, products are typically associated with multiple attributes, necessitating multiple extractions to obtain all corresponding values. In this work, we propose an Efficient product Attribute Value Extraction (EAVE) approach via lightweight sparse-layer interaction. Specifically, we employ a heavy encoder to separately encode the product context and attribute. The resulting non-interacting heavy representations of the context can be cached and reused for all attributes. Additionally, we introduce a light encoder to jointly encode the context and the attribute, facilitating lightweight interactions between them. To enrich the interaction within the lightweight encoder, we design a sparse-layer interaction module to fuse the non-interacting heavy representation into the lightweight encoder. Comprehensive evaluation on two benchmarks demonstrate that our method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. Our code is available \href{https://anonymous.4open.science/r/EAVE-EA18}{here}.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06839
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction
Yang, Li
Wang, Qifan
Chi, Jianfeng
Liu, Jiahao
Wang, Jingang
Feng, Fuli
Xu, Zenglin
Fang, Yi
Huang, Lifu
Liu, Dongfang
Computation and Language
Product attribute value extraction involves identifying the specific values associated with various attributes from a product profile. While existing methods often prioritize the development of effective models to improve extraction performance, there has been limited emphasis on extraction efficiency. However, in real-world scenarios, products are typically associated with multiple attributes, necessitating multiple extractions to obtain all corresponding values. In this work, we propose an Efficient product Attribute Value Extraction (EAVE) approach via lightweight sparse-layer interaction. Specifically, we employ a heavy encoder to separately encode the product context and attribute. The resulting non-interacting heavy representations of the context can be cached and reused for all attributes. Additionally, we introduce a light encoder to jointly encode the context and the attribute, facilitating lightweight interactions between them. To enrich the interaction within the lightweight encoder, we design a sparse-layer interaction module to fuse the non-interacting heavy representation into the lightweight encoder. Comprehensive evaluation on two benchmarks demonstrate that our method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. Our code is available \href{https://anonymous.4open.science/r/EAVE-EA18}{here}.
title EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction
topic Computation and Language
url https://arxiv.org/abs/2406.06839