Lune

EMNLP Findings2024

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

Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu

Abstract

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 here.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on15

  1. Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text ModelsJianmo Ni, Gustavo Hernández Ábrego, Noah Constant, Ji Ma et al.ACL Findings 2022 · 358 citations
  2. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence ScoringSamuel Humeau, Kurt Shuster, Marie-Anne Lachaux, Jason WestonICLR 2020 · 316 citations
  3. Learning to Extract Attribute Value from Product via Question Answering: A Multi-task ApproachQifan Wang, Li Yang, Bhargav Kanagal, Sumit Sanghai et al.KDD 2020 · 75 citations
  4. DeFormer: Decomposing Pre-trained Transformers for Faster Question AnsweringQingqing Cao, Harsh Trivedi, Aruna Balasubramanian, Niranjan BalasubramanianACL 2020 · 61 citations
  5. Multimodal Joint Attribute Prediction and Value Extraction for E-commerce ProductTiangang Zhu, Yue Wang, Haoran Li, Youzheng Wu et al.EMNLP 2020 · 46 citations

Related papers

  1. MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value ExtractionLi Yang, Qifan Wang, Jingang Wang, Xiaojun Quan et al.ACL Findings 2023 · 23 citations
  2. Knowledge-Selective Pretraining for Attribute Value ExtractionHui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang et al.EMNLP Findings 2023 · 1 citation
  3. SMARTAVE: Structured Multimodal Transformer for Product Attribute Value ExtractionQifan Wang, Li Yang, Jingang Wang, Jitin Krishnan et al.EMNLP Findings 2022 · 12 citations
  4. Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE TaskYupeng Zhang, Shensi Wang, Peiguang Li, Guanting Dong et al.ACL Findings 2023 · 9 citations
  5. TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product CategoriesGiannis Karamanolakis, Jun Ma, Xin Luna DongACL 2020 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines